# Stanford CS 224N | Project Reports

https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/project.html

[CS224N Home](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/index.html)
  * [Coursework](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/index.html#coursework)
  * [Schedule](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/index.html#schedule)
  * [Office Hours](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/office_hours.html)
  * [Final projects](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/project.html)
  * [Lecture Videos](https://canvas.stanford.edu/courses/191439/external_tools/3367)
  * [Ed Forum](https://edstem.org/us/courses/57406)


[ ![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/stanford-nlp-logo-new.jpg) ](http://nlp.stanford.edu/) [ ![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/stanfordlogo.jpg) ](http://stanford.edu/)
# CS224N: Natural Language Processing with Deep Learning
### Stanford / Spring 2024
## Final poster session
We thank our sponsors: Forethought, Hudson River Trading, Hugging Face, and Sky9 Capital, for supporting the poster session!   
  
The poster session was held at the [McCaw Hall and Ford Gardens](https://maps.app.goo.gl/MYgtYPLv61NKsj3G6) from 11 AM to 3 PM on Monday, June 10th, 2024.   
  

![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/sponsors/HRT.png) ![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/sponsors/Forethought.png) ![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/sponsors/HuggingFace.png) ![](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/images/sponsors/sky9.jpg)
## Prizes
Congratulations to the following teams, who produced exceptional, prize-winning projects! 
### Sponsor's prize for best poster
  * **[Intrinsic Systematicity Evaluation: Evaluating the intrinsic systematicity of LLMs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256735373.pdf)**. Ayush Chakravarthy. 


### Student choice for best poster
  * **[Enhancing Partisanship Prediction in Congressional Speeches](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912047.pdf)**. Amelia Leon, JB Jong Beom Lim, Sherry Yang. 


## Custom Projects  
| Project name  | Authors  |  
| --- | --- |  
| AmzBERT: Enhanced Multi-Label Sentiment Classification for E-commerce Product Reviews  | Zack Seifert  |  
| Weakly Supervised Automated Language Model Red-Teaming to Identify Likely Toxic Prompts  | Houjun Liu  |  
| Patent Classification Using Large Language Models  | Luke Mizuhashi  |  
| [Text as outcome: Topic models within a causal inference framework](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256564135.pdf)  | Juliette Coly  |  
| Mining Molecular Logics through Human Language: Predicting and Decoding Transcription Factor Logics on Gene Expression through LLM and transformer  | Gyu (Gyuhyeon) Kim  |  
| [From Infant to Toddler to Preschooler: Analyzing Language Acquisition in Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256656329.pdf)  | Yash Shah  |  
| [Using Iterative Back-Translation to Improve Neural Poetry Translation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256663652.pdf)  | Andrew Chen  |  
| [Interpreting parking signs with lightweight large language models (LLMs)](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256667022.pdf)  | Uche Ochuba  |  
| Exploring Themes and Outliers in CFPB Consumer Complaints  | Jonathan Hague  |  
| [Intelligent Interactive Large Language Model Planner: Responsive Personalized HomeRobot](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256691877.pdf)  | Angel Zhang, Gadi Mark Sznaier Camps  |  
| [Classification of clinical syndromes from patient-reported symptoms on social media](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256694719.pdf)  | Evan Maestri  |  
| [Transfer learning in audio-based emotion detection: surprising generalizability and limitations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256696905.pdf)  | Shunyu Yao  |  
| [ReaL Stories: RL for Adaptive AI Storytelling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256701070.pdf)  | Aditya Sood, Aniket Mahajan, Ayaan Chand  |  
| [Tailor-Made or Off-the-Rack? Comparing Domain-Specific and General-Domain Language Models on a Financial NLP Task](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256701224.pdf)  | Irina Alexandra Marton  |  
| [Cross attention for Text and Image Multimodal data fusion](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256711050.pdf)  | Dongyeong Kim  |  
| [Comparative Analysis of Foundation Models for Hospital Integration](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256722488.pdf)  | Suhana Bedi, Miguel Fuentes  |  
| Active learning in DPO through gradient portfolio optimization  | Josh Leib Kazdan, Ziang Song  |  
| [GRAFT: Graph Retrieval Augmented Fine Tuning for Multi-Hop Query Summarization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256724569.pdf)  | Sunny Yu, Natalia Kokoromyti, Sonya Shi Jin  |  
| [Diverse LLM Approaches in Essay Scoring: A Comparative Exploration of Many-Shot Prompting, LLM Jury Panels, and Model Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256725164.pdf)  | Alexa Sparks, Matias Hoyl, Rizwaan Malik  |  
| [Optimizing Large Language Models to Solve Crossword Puzzles](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256725260.pdf)  | Ishan Mehta, Andrew Lipschultz, Ohm Patel  |  
| [KAN-based Distillation in Language Modeling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256726249.pdf)  | Nick Mecklenburg  |  
| [Handle With Care! A Mechanistic Case Study of DPO Out-of-Distribution Extrapolation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256728108.pdf)  | Ryan Park  |  
| [Punk or Funk: Understanding the Performance of RoBERTa on Music Genre Classification](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256728728.pdf)  | Andrew Bempong, Deveen Harischandra  |  
| [Sparse Full-Rank MLPs for Increased Efficiency of Language Modeling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256731769.pdf)  | Aaryan Singhal, Quinn McIntyre  |  
| [How Important is the Truth?](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732105.pdf)  | Rehaan Ahmad, Joseph Tan  |  
| [Catch Me If You DAN: Outsmarting Prompt Injections and Jailbreak Schemes with Recollection](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732118.pdf)  | Alice Guo, Grace Jin, Jenny Wei  |  
| Query based Multi-document Summarizer and Image Synthesizer  | Geeta Jakkamsetti  |  
| [Finish Your Peas! Utilizing Multi-Label ImageClassification to Identify Food Items and Ingredients for Recipe Suggestions and Reducing Food Waste](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732895.pdf)  | Arianna Damiani, Prashaant Ranganathan  |  
| Engagement-based response selection for open-domain dialogue  | Marcelo Peña  |  
| [FlowState: Composing foundation models and retrieval for issue priority level prediction](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256734239.pdf)  | Alex Gilbert, Gustavs Zilgalvis  |  
| [Beyond IID Constraints: A Novel Approach to Identity Preference Optimization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256735149.pdf)  | Amirhossein Afsharrad  |  
| [Intrinsic Systematicity Evaluation: Evaluating the intrinsic systematicity of LLMs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256735373.pdf)  | Ayush Chakravarthy  |  
| [Numerous Multi-Pivot and Chained Pivot NMT for Low-Resource Language Translation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736440.pdf)  | Cees Armstrong, Kevin Reso  |  
| Enhancing Language-Concordant Clinical Text Translation with Zero-shot NER  | Ivan Lopez, Min Woo Sun  |  
| [Better Call Sheared-LLaMA-2.7B: Optimized Summarization for Legal Documents](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736730.pdf)  | Varun Madan, Arunima Srivastav  |  
| [Adapting Listen, Attend, and Spell to Enhance Brain-Computer Interfaces for Speech Decoding](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736750.pdf)  | Dylan Iskandar, Brian Ni, Vedant Singh  |  
| [Narrative Detection Across Nations in Online Social Media Discourse](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736764.pdf)  | Sungbin Kim, Khaled Messai, Vikram Srinivasan  |  
| [The First Proteinbender: A Novel "Structure-based Protein Search Engine"](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736780.pdf)  | Ethan Zhang, Saahil Sundaresan, Zane Chan  |  
| [Investigating Language Model Cross-lingual Transfer for NLP Regression Tasks Through Contrastive Learning With LLM Augmentations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736887.pdf)  | Raghav Ganesh, Raj Palleti  |  
| [Chinese Poem Generator with Prefix Control](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256800913.pdf)  | Yitong Lu  |  
| [DeviceBERT: Applied Transfer Learning With Targeted Annotations and Vocabulary Enrichment to Identify Medical Device and Component Terminology in FDA Recall Summaries](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256801068.pdf)  | Miriam Farrington  |  
| [L-LLM: Large Language LEGO Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256804765.pdf)  | Alex Wang, Calvin Laughlin  |  
| [Adapting BERT to non-Western Dialects: A Case Study on Nigerian Pidgin English Slurs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256807393.pdf)  | Sathvik Nori, Adrian Adegbesan  |  
| [Words and Wins: Enhancing Game Play with LLM Fine-Tuning by RL](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256808758.pdf)  | Xuanzi Chen, Zhengjia Huang  |  
| [From Preferences to Principles: Automated Principle Generation for Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256830561.pdf)  | William Fang, Vikram Sivashankar  |  
| From Lies to Insights: Expanding and Understanding the LIAR Dataset  | Felix Zhan  |  
| [HieroLM: Egyptian Hieroglyph Recovery with Next Word Prediction Language Model](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256832201.pdf)  | Xuheng Cai, Erica Zhang  |  
| Analyzing Sophia's Gradient Distributions in Language Model Pretraining  | Raghav Kapoor  |  
| [Investigating Improvement to English-Tigrinya Translation via Transfer Learning Over Varying Languages](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256838722.pdf)  | Abel Dagne, Sheden Andemicael  |  
| [Quality or Quantity? Comparing Domain-Adaptive Pre-training Approaches for Language Models with Mathematical Understanding](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256838758.pdf)  | Christine Ye, Alexandre Acra  |  
| [Knowledge-Enhanced Language Models: A Comparative Study of RAG and Embedding Methods](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256839576.pdf)  | Adarsh Ambati, Nikash Chhadia  |  
| [Optimizing Language Models for Safe Online Discourse: Developing Metrics and Models for Detoxifying Internet Conversations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256840631.pdf)  | Steven Li, Steven Le  |  
| [Making Silicon Sing](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256841647.pdf)  | Kadija Ismail, Imen Kedir  |  
| [Active Learning for Efficient NLP Training](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256843367.pdf)  | Daniel Lee, Thomas Yim, Ibrahim Dharhan  |  
| [Character Understanding in Literary Texts: Leveraging TinyLlama for Advanced Character Analysis in the LiSCU Dataset](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844138.pdf)  | Katherine Wong  |  
| [arXivBot: A Large Language Model Chatbot That Has High Factuality and Coverage by Few-Shot Grounding on arXiv](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844327.pdf)  | Xiaofeng Tang  |  
| [SENTINEL: A Heterogeneous Ensemble Framework for Detecting AI-Generated Text in the Era of Advanced Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844435.pdf)  | Natalie Cao, Haocheng Fan  |  
| [Predicting Stock Market Trends from News Articles And Price Trends using Transformers](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844806.pdf)  | Kasra Naftchi-Ardebili, Karanpartap Singh  |  
| [Merging ‘Personas’ in Multi-Agent Systems of Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844931.pdf)  | Andy Dai, Sriya Mantena  |  
| Critical Learning Periods for Second Language Acquisition in Neural Language Models  | Daniel Wurgaft, Jerome Han  |  
| [Enhancing Practice Problem Retrieval with Deep Learning: A Rewriter-Retriever-Reranker Approach](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846228.pdf)  | Charles Joyner, Ronny Junkins, Mack Smith  |  
| [Can LLMs Survive in the Desert? Evaluating Collaborative Capabilities of Generative Agents on a Classic Team-Building Problem](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846460.pdf)  | Yash Narayan, Daniel Shen, Ethan Zhang  |  
| SceneGrounder: Natural Language Scene Descriptions and Retrieval Augmented Generation for 3D Visual Tasks  | Huy Nguyen, James Brown  |  
| [RubricEval: A Scalable Human-LLM Evaluation Framework for Open-Ended Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846781.pdf)  | Vineel Bhat  |  
| Medical Named Entity Recognition and Relation Extraction from Clinical Notes  | Ameya Jadhav, Sreyana Kukadia  |  
| The Invisible Author: Mapping AI Penetration in News Journalism  | Jun Wang, Andrew Zhang  |  
| Developing a GPT-Based Autonomous Agent With Novel Workflow Execution Capabilities  | Kenny Lam, Vaishnav Garodia  |  
| [Improving speech brain-computer interface with conversation context](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846904.pdf)  | Brian Lee, Allison Tee  |  
| [Negotiation Copilot: Exploring Ways to Build an AI Negotiation Assistant](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847026.pdf)  | Winson Cheng, Abhinav Agarwal  |  
| AuRA (Automated Retrieval-Augmented Generation (RAG) System Development)  | Robby Manihani  |  
| KoWhisper: Efficient Bilingual Speech-to-Text for Edge Deployment  | Jason Park, Harshit Gupta  |  
| [Enhancing AI Creativity: A Multi-Agent Approach to Flash Fiction Generation with Small Open-Source Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847192.pdf)  | Alex Wang, Berwyn Berwyn, Jermaine Zhao  |  
| [UltimateMedLLM-Llama3-8B: Fine-tuning Llama 3 for Medical Question-Answering](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847341.pdf)  | Jayson Meribe, Sean Zhang  |  
| [PROCEED: Performance Routing Optimization for Cost-Efficient and Effective Deployment](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847361.pdf)  | Lichu Acuña, Odin Farkas  |  
| [Improving Spanish-Mapudungun Translation through Transfer Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847445.pdf)  | Eban Ebssa  |  
| EDU-RAG: A RAG Benchmark with Web-enhanced Content in Education Domain. Will RAG Help AI Tutor?  | Xinxi Chen, Jingxu Gao  |  
| [Mapping the Mind: Knowledge-Graph Augmented Retrieval](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847497.pdf)  | Nicholas Vo  |  
| [Learning Semantic Complexities of NYT Connections](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847963.pdf)  | Emily Zhang, Yanan Jiang, Peixuan Ye  |  
| [SuLaLoM: Structured Classification of Tabular Data with Large Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256865785.pdf)  | Su Kara  |  
| AdaVid: Adaptive Video-Language Pretraining  | Chaitanya Patel  |  
| [PragMaBERT: Analyzing Pragmatic Markers in Political Speech](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256878985.pdf)  | Matt Wise, Houda Nait El Barj  |  
| [Robotic AssistEMT: An EMT Chatbot](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256889041.pdf)  | Aanika Atluri, Sarah Barragan, Anusheh Chaudry  |  
| Knowledge Distillation of Deep Language Models for Electrification Information Extraction from Building Permits  | Tony Liu  |  
| Shared Representation of Language in Broca’s Area and Large Language Models  | Alisa Levin, Benyamin Meschede-Krasa, Yun Hwang  |  
| ModelFusion  | Joong Kun Lee  |  
| [PragMaBERT: Analyzing Pragmatic Markers in Political Speech](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256905144.pdf)  | Matt Wise, Houda Nait El Barj  |  
| [Comparative study between addition of one MAMBA block to Wav2Vec2 Pretrained model and Vanilla Pretrained model](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256908412.pdf)  | Puchiss Panitpotjaman  |  
| [Multi-Task Alignment Using Steering Vectors](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256908428.pdf)  | Charles Li, Nahum Maru  |  
| [Project Oracle: Autoregressive Future Event Prediction with Sequential Modeling and Transformers](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909155.pdf)  | Brian Wu, Katherine Wang, Ismail Mardin  |  
| [DelT5: Dynamic Token Deletion for Efficient Byte-level Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909456.pdf)  | Julie Kallini  |  
| Formally Verify Generated Code  | Livia Sun  |  
| [Fine-tuning Digital Agents with BAGEL Trajectories](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909826.pdf)  | Alfred Yu, An Doan  |  
| [Optimal Brain Projection: Neural Network Compression using Mixtures of Subspaces](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256910038.pdf)  | Daniel Garcia  |  
| [Mistriply: Encoding Human Algorithmic Processes into LMs for Teaching and Computation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256910642.pdf)  | Harviel Kyle Arcilla, Colette Do  |  
| [Item Difficulty Modeling for a Sentence Reading Efficiency Task with Language Model Simulations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911547.pdf)  | Wanjing Anya Ma  |  
| [Improving Speech-to-Text Brain-Computer Interface Performance with Neural Decoders and Large Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911581.pdf)  | Laywood Fayne, Mohammad Rehan Ghori  |  
| Advancing Automated Content Moderation using Large Language Models  | Harshit Gupta, Sidhant Bansal, Sneha Jayaganthan  |  
| Leveraging Language Models for Multiclass Classification of Unfair Clauses in Terms of Service  | Shaurnav (Joy) Ghosh, Shrish Janarthanan  |  
| [Talk To Me, Your Virtual AI Therapist: Advancing AI-Driven Psychotherapeutic Engagement with Sentiment Analysis](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911736.pdf)  | George Birikorang, Nathan Paek, Zoe Lynch  |  
| [The impact of LLM pruning for fine-tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911740.pdf)  | Varun Shanker, Sarah Chung  |  
| [Curriculum Learning with TinyStories](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911763.pdf)  | Michail Christiaan Melonas  |  
| [Beyond Single Commands: Evaluating LLMs on Multiple Instruction Sequences](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911801.pdf)  | Sagnik Bhattacharya, Vaastav Arora, Prateek Varshney  |  
| [FinRAG: A Retrieval-Based Financial Analyst](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911814.pdf)  | Krrish Chawla, Allen Naliath  |  
| [ClimateGrantLLM: Benchmarking grant recommendation engines for natural language descriptions of climate resilient infrastructure capital projects](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911883.pdf)  | Bhumikorn Kongtaveelert, Auddithio Nag, Peter Li  |  
| [JEDI: Justifiable End-dialogue Driven Interaction for NPC Entities in Role-Playing Games](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911920.pdf)  | Willy Chan, Omar Abul-Hassan, Sokserey Sun  |  
| [Efficient Translation of Natural Language to First-Order Logic Using Step-by-Step Distillation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911952.pdf)  | Aliyan Ishfaq, Shreyas Sharma  |  
| [Enhancing Partisanship Prediction in Congressional Speeches](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912047.pdf)  | Amelia Leon, JB Jong Beom Lim, Sherry Yang  |  
| [Needle in a Haystack: Probing Transformer Capabilities to Recognize Non-Star-Free Languages](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912125.pdf)  | Richard Gu, Sambhav Gupta, Andy Tang  |  
| [Forticode: A Benchmark for Evaluating the Robustness of Code Generation Models Against Adversarial Syntax Preserving Mutations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912126.pdf)  | Amrit Baveja, Anant Singhal  |  
| [Disarming Sleeper Agents: A Novel Approach Using Direct Preference Optimization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912147.pdf)  | Katherine Worden, Jeong Shin  |  
| [Now You See Me: Vision-enhanced BERT for obfuscated text abuse detection](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912376.pdf)  | Dylan Zhou  |  
| [The Potential of Large Language Models in Assisting Data Augmentation for East Asian Digital Humanities](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256917125.pdf)  | Fengyi Lin  |  
| [Expanding Horizons in RAG: Exploring and Extending the Limits of RAPTOR](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256925521.pdf)  | Alex Laitenberger  |  
| [The Shades of Meaning: Investigating LLMs’ Cross-lingual Representation of Grounded Structures](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256925875.pdf)  | Pinlin [Calvin] Xu, Garbo Chung  |  
| [FolioLLM: Constructing portfolio of ETFs using Large Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256938687.pdf)  | Andrey Popov, Oleg Roshka  |  
| [Integrating Domain Knowledge for Financial QA: A Multi-Retriever RAG Approach with LLMs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256942674.pdf)  | Yukun Zhang, Stefan Elbl Droguett, Samyak Jain  |  
| [Integrating Extra Linguistic Meaning into the BERT Framework](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256957654.pdf)  | Riley Carlson, Bradley Moon, Ishaan Singh   |  
| A Contextual Approach Towards Financial Sentiment Analysis  | Emma Sun  |  
| [Enhancing Construction Project Management through a Cross-Modal Retrieval System](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256963847.pdf)  | Jayadev Rajan  |  
| Large language models for sustainable food design  | Anna Thomas  |  
| [News to Numbers: NLP Stock Return Predictions](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256968470.pdf)  | Shree Reddy, Henrique B. N. Monteiro, Lucas Werneck  |  
| Apollo: A Large Multi-Modal Model Capable of Sampling Videos at 8fps  | Orr Zohar  |  
| [Analyzing the Effectiveness of Morphologically Motivated Tokenization on Machine Translation for Low-Resource Languages](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256974654.pdf)  | Abhishek Vangipuram, Emiyare Ikwut-Ukwa, William Huang  |  
| [Hivemind: An Architecture to Amalgamate Fine-Tuned LLMs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256976188.pdf)  | Matthew Mattei, Matt Hsu, Ramya Iyer  |  
| Leveraging Long Context for Customer Support  | Ian Lim  |  
| [Course Recommendation Chatbot](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256979487.pdf)  | Naama Bejerano, Emma Troast  |  
| From Headlines to Bottom Lines: Leveraging Earning Releases and News Headlines to Predict Stock Price Movement  | Ananya Krishnan, Jinny Chung, Charles Shaviro  |  
| [Leverage Augmented Large Language Models to build Hyper Personalized Recommendation Systems](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256980295.pdf)  | Viveak Ravichandiran  |  
| [Retrieval Augmented Verilog Generation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256982092.pdf)  | Joseph Rejive  |  
| Parsing FDA label data with LLMs  | Jake Silberg  |  
| [FAST: Finetuning Agents with Synthetic Trajectories](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256984105.pdf)  | Flor Lozano-Byrne  |  
| [Diving Under the Hood: Exploring LLM Conceptual Understanding Through Latent Embeddings](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256984984.pdf)  | Kelvin Nguyen  |  
| [Korean-English Neural Machine Translation with Language Style Control](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256985783.pdf)  | Jiwon Jeong, Hyejin Lee, Youjin Song  |  
| [Using Segmented Novel Views, Depth, and BERT Embeddings for Training in Robot Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256985788.pdf)  | Matt Strong  |  
| [How Much Attention is "All You Need"?](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256987290.pdf)  | Ignacio Fernandez, Duru Irmak Unsal  |  
| [A case for pre-training in Compositional Generalization tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256987641.pdf)  | Ahmad Jabbar, Rhea Kapur  |  
| RubricEval - Scalable Human-LLM Evaluation of LLMs on Open-Ended Tasks Using Human-Written Rubrics  | Stella Zhang  |  
| [MuRST: Multilingual Recursive Summarization Trees](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256987799.pdf)  | Tarini Mutreja, Saron Samuel, Humishka Zope  |  
| [Simulating the Court: Legal Judgment Prediction through Relational Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988211.pdf)  | Ein Jun  |  
| [An Exploration of Transferring Domain Expertise](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988324.pdf)  | Jonathan Paul Hsu  |  
| [Posetta: Language-Guided Protein Design](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988454.pdf)  | Haotian Du, Jingjia Liu, Tianyu Lu  |  
| [Self Reward Scaling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988631.pdf)  | Arjun Chandran  |  
| [Optimizing Human-Agent Interaction: Evaluating Diverse Strategies for Human Input in the OptiMUS LLM Agent System](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988763.pdf)  | Idil Defne Çekin, Isaiah Hall  |  
| A Neuro-Symbolic Integration of LLMs and SMT-solvers for Trustworthy Logical Reasoning  | Harun Khan  |  
| [Experiments on Multi-Task Learning Framework over BERT for Performing Sentiment Analysis, Paraphrase Detection, and Semantic Textual Similarity Simultaneously](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988876.pdf)  | Florence Chen  |  
| [arXivBot](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988967.pdf)  | Amr Sherif  |  
| [Robust DPO with Convex-NN on Single GPU](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989002.pdf)  | Miria Feng  |  
| DNACLIP: Contrastive representation learning for joint embedding of DNA and natural language  | Brian Kang  |  
| [Taming Guidelines in the Wild](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989143.pdf)  | Anuj Iravane  |  
| Long Horizon Robotic Manipulation through Closed-Loop Mark-Based Visual Prompting  | David Ihim  |  
| Context-Aware Gesture Interpretation in Augmented and Virtual Reality  | Trishia El Chemaly  |  
| [Reading Between the Minds: Context-Aware Brain-to-Text Decoding](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989378.pdf)  | Ellie Tanimura, Sarosh Khan  |  
| [Clinical Text Summarization with LLM-Based Evaluation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989380.pdf)  | Daphne Barretto, Matthew Jin, Bora Oztekin  |  
| Beauty and a Beat: Comparing and Combining the Utility of Lyrical and Acoustic Features to Identify Genuine Playlists  | Naomi Eigbe  |  
| [Tracing the Development of Word Meaning During Training](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989451.pdf)  | Shenghua Liu, Yiheng Ye  |  
| MoonSpeech - Training a tiny multi-modal LLM  | Krishna Dusad  |  
| Integrating Clinical Note Synthesis with Synthetic EHR Data for Enhanced Healthcare Analysis  | Jessica Yang, Riya Karumanchi  |  
| Automated Extraction and Detection of Selective Reporting in Publications of Landmark Cancer Trials  | Maximilian Schuessler, Amanda Rodriguez, Selina Pi  |  
| An LLM-Based Recommender System for Scientific Papers  | Vijay Josephs, Aaron Reed  |  
| Actions versus Objects: Understanding Gendering of Jobs through Language  | Echo Yan Zhou  |  
## Default Projects  
| Project name  | Authors  |  
| --- | --- |  
| [Enhancing minBERT for Multi-Task NLP: Architectural and Training Innovations](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256511391.pdf)  | Xinxie Wu  |  
| [Enhancing multi-task fine-tuning on BERT-based model](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256525389.pdf)  | Xiaochen Xiong  |  
| [Task-Specific Parameter Efficient Fine-Tuning for Improving Multitask BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256598767.pdf)  | Brian K. Ryu   |  
| [Adapt BERT on Multiple Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256612936.pdf)  | Ran Li  |  
| [Post-Op BERT: Improving Gradient-Surgery on Imbalanced Data](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256689450.pdf)  | Giancarlo Ricci  |  
| [Improving Semantic Meaning of BERT Sentence Embeddings](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256697927.pdf)  | Timothy Yao  |  
| [Improving the Performance of BERT Using Contrastive Learning and Meta-Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256707873.pdf)  | Akash Gupta, Justin Shen, Peter Westbrook  |  
| [Fine-Tuning BERT for Multi-Task Prediction](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256710549.pdf)  | Uma Dayal  |  
| Robust Adaptation of BERT using SMART  | Ozgur Cetin  |  
| [Improving minBERT with Conditional Layer Normalization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256727006.pdf)  | Matan Abrams  |  
| [Multi-task Learning with minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256728134.pdf)  | Praneet Bhoj  |  
| optiBERT: Fine-Tuning BERT for Optimal Performance  | Jirah Taylor  |  
| [Multitask Finetuning for MinBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732436.pdf)  | Ethan Boneh  |  
| [ConCATenation Curiosity: Evaluating Multitask Performance of minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732598.pdf)  | Prithvi Krishnarao, Emily Redmond  |  
| [Parameter Efficient Fine-Tuning for Multi-Task BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256732792.pdf)  | Zhen Wu, Genghan Zhang, Alexa Hu  |  
| [Multi-task BERT Fine-Tuning with Gradient Tricks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256733006.pdf)  | Henry Ang  |  
| [PowerBERT: Improving BERT with a Power Set Ensemble of Fine-Tuned Single and Multitask Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256733128.pdf)  | Eric Lee, Kevin Song, Jeanette Han  |  
| [PALs of MTL: Investigating Task Scheduling Algorithms in the Presence of PALs](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256735000.pdf)  | Kris Jeong, Pauline Arnoud  |  
| [BERT with LORA: Low-rank Adaptation Of Large Language Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736504.pdf)  | Tolu Oyeniyi  |  
| [From BERT to Brilliance: An Analytical Approach to Advancing Multitask Learning for NLP](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736653.pdf)  | Akea Pavel, Adrian Mendoza-Perez  |  
| [Comparing BERT Fine-Tuning Methods](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736657.pdf)  | Adrian Stoll, Jennifer Ho, Daniel Tyshler  |  
| Dynamic Weight Adjustment for Multitask BERT: An Approach to Sentiment, Paraphrase, and Similarity Tasks  | Marco Pizarro  |  
| Multitask training BERT for Sentiment Analysis, Semantic Textual Similarity, and Paraphrase Detection  | Feiyang Kuang  |  
| [BERT Multitask Methods for Low-Parameter Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736861.pdf)  | Elton Manchester  |  
| [miniBert Unleashed](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736952.pdf)  | John Cao, David Kwentua  |  
| [Implementing and Enhancing minBERT for Optimized Performance on Multiple Downstream Classification Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256736971.pdf)  | Priti Rangnekar  |  
| [Multi-BERT: Investigating Methods for BERT Multitask Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256818152.pdf)  | Zach Benton  |  
| [Expanding minBERT’s Scope: Integrating SimCSE, Ensemble Learning, and PANDA](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256821519.pdf)  | Yasmina Abukhadra, Samantha Liu, Hannah Norman  |  
| [Parameter Efficient BERT Fine-tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256827366.pdf)  | Ang Li  |  
| [Hybrid BERT: Sharing Layers for Multitask Performance with Fewer Parameters](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256830973.pdf)  | Jake North, Jared Weissberg  |  
| [Rhapsody on a Theme of Gradient Surgery: Variations to Improve minBERT for Multi-Task Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256837554.pdf)  | Christian Femrite  |  
| [minBERT Multi-Extended: Fine Tuning minBERT for Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256838700.pdf)  | Jayna Huang, Isabella Lee, Sophie Zhang  |  
| [BEES: Bi-Encoder Ensembles with Simple Contrastive Learning and Smoothness Induced Adversarial Regularization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256839766.pdf)  | Nithish Kaviyan Dhayananda Ganesh  |  
| [minBERT and Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256842696.pdf)  | Bay Foley-Cox, David Wendt  |  
| [Too SMART for your own good: Multitask Fine-Tuning pre-trained minBERT through Regularized Optimization and hyper-parameter optimization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256843679.pdf)  | Proud Mpala, Wayne Chinganga  |  
| [MathBERT: Increasing mathematical reasoning through Domain-Specific Fine-tuning and Optimization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256843987.pdf)  | John Founds, Carlos Santana  |  
| [Implementing and Fine-Tuning BERT for Sentiment Classification, Paraphrase Detection and Semantic Similarity Analysis](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256844739.pdf)  | Anqi Zhu, Antonio Torres Skillicorn, Kyra Sophie Kraft  |  
| [BERT and Multitask Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256845880.pdf)  | Sureen Heer, Collin Jung, Adrian Molofsky  |  
| [A Better Multitask BERT: Improving on Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846084.pdf)  | Andrea Hurtado, Sarah Teaw  |  
| [Optimizing Multitask BERT: A Study of Sampling Methods and Advanced Training Techniques](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846196.pdf)  | Andrew Wu, Wesley Larlarb  |  
| [YourBERT: Tailoring BERT for Precision](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846268.pdf)  | Paolo Tayag, Jack Walter  |  
| [Utilizing Enhanced Deep Contextualized Word Embeddings for Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256846676.pdf)  | Renaldo Venegas, Ethan Yuen  |  
| [BERT on Multitask Training: Bimodality, Ensemble, Round-robin, Text-encoding, and More](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847077.pdf)  | Jiaxiang Ma, Yuchen Deng  |  
| [Untitled](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847264.pdf)  | Betty Wu  |  
| [Cooking A Multitude of Optimizations for BERT Multi-Task Mastery](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847358.pdf)  | Michael Cho, Michael Peter Hong, Michael Marcotte  |  
| [Multi-Dimensional BERT: Bridging Versatility and Specialization in Multi-Task Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256847376.pdf)  | Emma Casey, Luke Moberly  |  
| [Fine-tuning BERT for Multi-task Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256850229.pdf)  | Yutai Luo  |  
| [Multitask and Task-specific Optimizations for minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256851463.pdf)  | James Chen, Krish Parikh  |  
| [Utilizing minBERT for Multiple Sentence-level Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256856640.pdf)  | Qianhui Zheng  |  
| [(Multi-gate) Mixture of ExBerts](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256861594.pdf)  | O Sub Kwon  |  
| minBERT and Downstream Tasks  | Zhihua Cai  |  
| [Fine BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256865732.pdf)  | Xavier Millan, Yuvraj Baheti, Andrew Nguyen  |  
| [UnBERTlievable: How Extensions to BERT Perform on Downstream NLP Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256867713.pdf)  | Sophie Andrews, Naomi Boneh  |  
| [PALs and MNRL: Adaptations for Multi-Task BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256868981.pdf)  | Lei Yin  |  
| [Multitask BERT Fine-Tuning and Generative Adversarial Learning for Auxiliary Classification](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256877201.pdf)  | Christopher Sun, Abishek Satish  |  
| [SMART Fine-tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256900864.pdf)  | Zikui Wang  |  
| [SLOTH: Semantic Learning Optimization and Tuning Heuristics for Enhanced NLP with minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256904367.pdf)  | Phillip Miao, Cici Hou  |  
| [Multitask Learning with BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256904567.pdf)  | Sanjaye Elayattu  |  
| [An Exploration of Multi-Task Learning over minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256906365.pdf)  | Chunming Peng, Max Yuan, Annie Wang  |  
| minBert with Cosine Similarity and PCGrad  | Xiyuan Wu, Alan Zhang  |  
| [BERT: Battling Overfitting with Multitask Learning and Ensembling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256907158.pdf)  | Javier Nieto, Annabelle Jayadinata  |  
| [Strategies for Building Semantic Classification Dataset with LLM and Active Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256907584.pdf)  | Jerry Chan  |  
| [BERT Goes to School: Improving BERT Embeddings Through Curriculum-Based Contrastive Learning and Synonym-Based Data Augmentation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256908474.pdf)  | Arnav Gangal, Martin Pollack, Russell Tran  |  
| [Bagging the Singular Value Decomposition - A Joint Implementation of LoRA and Bootstrap Aggregating as a Fine-tuning Regime](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256908489.pdf)  | Andri Vidarsson, Jacob Thornton, Raphaëlle Ramanantsoa  |  
| [Research on the Application of Deep Learning-based BERT Model with Additional Pretraining and Multitask Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909165.pdf)  | Muran Yu, Ricky Liu  |  
| [My PAL BERT: Using Projected Attention Layers and Additional Fine-Tuning Strategies to Improve BERT’s Performance on Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909596.pdf)  | Colin Michael Sullivan, Abhishek Kumar  |  
| [Enhancing Multi-Task Learning with BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909607.pdf)  | Josiah Griggs  |  
| [minBERT-based Multitask Model using PAL-LoRA](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256909948.pdf)  | Xian Wu  |  
| [Enhacing minBERT by Leveraging CosineEmbeddingLoss Fine-Tuning and Multi-Task Learning with Gradient Surgery](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256910126.pdf)  | Peter De La Cruz, Mohamed Musa, Yahaya Ndutu  |  
| [Orthogonal Projection Loss for Multi-Headed Attention](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256911915.pdf)  | Kyle McGrath  |  
| [Enhancing Dev Accuracy with DoRA](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256912017.pdf)  | Hayden Kim, Nilson Rodriguez Cadenas  |  
| [SMARTer Multi-task Fine-tuning of BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256913223.pdf)  | Disha Ghandwani, Aditya Ghosh, Rahul Kanekar  |  
| [Tuning Up BERT: A Symphony of Strategies for Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256915648.pdf)  | Nick Soulounias  |  
| [AllBERT: Mastering Multiple-Tasks Efficiently](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256920087.pdf)  | Thierry Rietsch, Joe Serrano  |  
| [Beyond BERT: a Multi-Tasking Journey Through Sampling, Loss Functions, Parameter-Efficient Methods, Ensembling, and More](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256922496.pdf)  | Alycia Lee, Amanda Li  |  
| [Enhancing BERT’s Performance on Downstream Tasks via Multitask Fine-Tuning and Ensembling](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256924513.pdf)  | Lianfa Li  |  
| [minBert and Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256924872.pdf)  | Zhimin Tang  |  
| Multitask Contrastive Learning for Sentence Representation  | Abdulaziz Alharbi  |  
| [BERT’s Got Talent: Advanced Fine-Tuning Strategies for Better BERT Generalization](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256935585.pdf)  | Grace Luo, Danny Lin  |  
| Separating Meaning From Weights in Sentence Embeddings  | Haibib Kerim  |  
| [A multi-objective approach to improving accuracy and efficiency in multitask BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256940449.pdf)  | Arpit Singh, Amitai Porat, Lin Ma  |  
| [Supercharging MinBERT with Contrastive Learning & Self-Distillation](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256940490.pdf)  | Cécile Logé Baccari  |  
| [Parameter-Efficient Adaptation of BERT using LoRA and MoE](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256942242.pdf)  | Li-Heng Lin, Yi-Ting Wu  |  
| [Exploring Multi-Task Learning with Unbalanced Datasets and Gradient Surgery](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256942787.pdf)  | Julien Darve  |  
| [Multitask minBERT with Parameter-efficient Fine-tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256948220.pdf)  | Zhuoqi (Charlie) Zhang  |  
| [Enhanced BERT Adaptation: Ensembling LoRA Models for Improved Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256954154.pdf)  | Denis Tolkunov  |  
| [Parameter-Efficient Learning Strategies for Multi-Task Applications of BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256957238.pdf)  | Irmak Sivgin, Mahmut Yurt  |  
| Efficient multi-task learning strategies for single BERT  | Jiamin Sun, Xingjian Zhang  |  
| [Exploring Transfer Learning and Multi-Task Learning: An Experimental Analysis of Diverse Architectures](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256961132.pdf)  | Sayali Sonawane  |  
| [Improving Multi-Task BERT Fine-Tuning: Effective Methods and Practices](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256962947.pdf)  | Amy Wang, Haopeng Xue, Xinling Li  |  
| [minBERT and Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256963994.pdf)  | Ziyang Ding, Daniel Zou  |  
| [BERT Multitask Learning in a Semi-Supervised Learning Setup](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256966900.pdf)  | Danhua Yan  |  
| [BERTille, a multitask BERT model made in France](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256966928.pdf)  | Alexis Bonnafont, Malo Sommers, Salma Zainana  |  
| [Enhancing BERT:The Effects of Additional Pretraining Using Downstream Task Relevant Datasets](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256967485.pdf)  | Chase Nwamu  |  
| [Strategies for Optimization of minBERT for Multi-Task Learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256971312.pdf)  | Ankur Jai Sood, Cameron Heskett, Shinwoo Lee  |  
| [How to make your BERT model an xBERT in multitask learning?](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256975170.pdf)  | Xingshuo Xiao  |  
| [ComBERT: Improving Multitask-BERT with Combinations of Scale-invariant Optimization and Parameter-efficient Fine-tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256975181.pdf)  | Harper Hua, Ruiquan Gao , Xinyi(Jojo) Zhao  |  
| [Fine-tune miniBERT for multi-task learning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256978289.pdf)  | Geo Zhang  |  
| [Hybrid Multitask Learning with BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256979182.pdf)  | Anna Mattinger  |  
| [Improving minBERT on Downstream Tasks Through Combinatorial Extensions](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256979211.pdf)  | Yichen Jiang, Ria Calcagno, Senyang Jiang  |  
| [StudentBERT: Multitask Training with Teacher Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256980236.pdf)  | Shang Jiang, Shengtong Zhang  |  
| Balancing Act: Evaluating the Interactions Between Multi-Task Learning, Cosine Similarity, and Adversarial Regularization  | Leo Glikbarg, Dhafer Faishal  |  
| Build, Extend, Repeat, Triumph: Extensions to a BERT Multitask Model  | Oliver Lee, Ethan Hsu, Manat Kaur  |  
| [Fasting NLP:Slimming Down Models with QLoRA](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256980385.pdf)  | Ricardo Carrillo  |  
| [BEST-FiT: Balancing Effective Strategies for Tri-task Fine Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256980581.pdf)  | Elijah Kim, Rohan Sanda  |  
| [Extending minBERT in a Multi-Task Setting](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256982841.pdf)  | Jean-Philippe Lemay, Veljko Skarich, Joe Wang  |  
| [Multi-task Learning for BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256983806.pdf)  | Xinyan He, Wei Zhao  |  
| [Enhancing BERT with Adapter Fusion: A Strategy for Multi-Task Knowledge Transfer](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256983854.pdf)  | Hao Xu  |  
| [Combining Contrastive Learning with Layer Utility Analysis and Experimental Multi-Task Finetuning to Improve mini-BERT Performance](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256984634.pdf)  | Ellie Vela, Vionna Atef, Ethan Bogle  |  
| [minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256984897.pdf)  | Bryant Mendez Melchor, Gustavo Martinez  |  
| [minBERT and Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256985051.pdf)  | Jiajing Luo  |  
| Parameter Efficient Fine Tuning in Multi-Task Learning with minBERT  | Havin E. Hosgur  |  
| [BERTolomeu: Exploring Methods to Improve Downstream Task Performance with BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256985182.pdf)  | Flora Yuan, Jack Zhang  |  
| [Multi-Task Learning for Language Model Fine-Tuning](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256986159.pdf)  | Anonto Zaman  |  
| [PradrewBert: The Efficient One](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256986636.pdf)  | Pradyumna Saligram, Andrew Lanpouthakoun  |  
| Smarter BERT with Better Understanding and Generalization  | Yujie Gao  |  
| Multitask BERT for Sentiment Analysis, Paraphrase Detection, and Semantic Textual Similarity  | Brandon Ring  |  
| [Triple Threat: Exploring Multi-task Training Strategies for BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256987539.pdf)  | Sally Zhu, Akaash Kolluri  |  
| NeuSemble: Neural Ensemble of Multitask Learning with minBERT  | Youzhi (Yousef) Liang  |  
| Bidirectional Encoder Representations from Transformers (BERT) with Mixture of Experts for Sentiment Analysis, Paraphrase Detection, and Semantic Textual Similarity  | David D. Wu  |  
| [Fine-tuning BERT for Multiple Downstream Tasks](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988622.pdf)  | Jianhao Cai  |  
| [Parts of MinBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988649.pdf)  | Monica Hicks, Megan Liu  |  
| [Improving the performance of miniBERT and BERTaaR (BERT as a Recruiter)](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988665.pdf)  | Prabhjot Singh Rai, Jared Isobe  |  
| [Applying Multitask Fine-Tuning to Sentence-BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988838.pdf)  | Alvin Ayuyo  |  
| [Investigation of BERT Fine-tuning Strategies](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988931.pdf)  | Sheena Lai  |  
| [BERT-Based Multi-Task Learning for Natural Language Understanding](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256988943.pdf)  | Ray Ortigas  |  
| [Fine-tuning and Gender Fairness of BERT Models](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989136.pdf)  | Kevin Rizk  |  
| Improving minBert using Multi-Task Fine-Tuning with cosine-similarity  | Eun Sun Song  |  
| [Exploring Efficient Learning of Small BERT Networks with LoRA and DoRA](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989355.pdf)  | Aditri Bhagirath, Moritz Bolling, Daniel Frees  |  
| Downsizing minBERT without hurting performance  | Nazar Khan  |  
| [Leveraging PEFT Strategies for Improved Performance and Efficiency in minBERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989415.pdf)  | Mateo Quiros Bloch, Lara Seyahi, Susan Ahmed  |  
| [Mastering minBERT: A True Balancing Act](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/256989435.pdf)  | Emma Escandon, Alejandro Rivas, Daniela Uribe  |  
| [Minh-BERT](https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/final-reports/257186901.pdf)  | Taran Kota  |