Princeton Natural Language Processing

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

tree-of-thought-llm

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

ALCE

[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

AutoCompressors

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

LESS

Preprint: Less: Selecting Influential Data for Targeted Instruction Tuning

WebShop

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

intercode

[NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898

TransformerPrograms

[NeurIPS 2023] Learning Transformer Programs

CEPE

Preprint: Long-Context Language Modeling with Parallel Encodings

QuRating

Selecting High-Quality Data for Training Language Models

NLProofS

EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443

LLMBar

[ICLR 2024] Evaluating Large Language Models at Evaluating Instruction Following

MQuAKE

[EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

USACO

Can Language Models Solve Olympiad Programming?

LM-Kernel-FT

A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643

c-sts

[EMNLP 2023] C-STS: Conditional Semantic Textual Similarity

Collie

[ICLR 2024] COLLIE: Systematic Construction of Constrained Text Generation Tasks

MABEL

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975

LM-Science-Tutor

PTP

Improving Language Understanding from Screenshots. Paper: https://arxiv.org/abs/2402.14073

corpus-poisoning

[EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156

SocraticAI

Problem solving by engaging multiple AI agents in conversation with each other and the user.

lwm

We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effectively control these agents through verbal communication.

Heuristic-Core

The code accompanying the paper "The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models" - https://arxiv.org/abs/2403.03942

il-scaling-in-games

Official code repo of "Scaling Laws for Imitation Learning in NetHack"

MoQA