Princeton Natural Language Processing

All

82 repositories

SWE-agent
Public
[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
agent ai cybersecurity lms developer-tools agent-based-model llm
Python
•
MIT License
•1.4k•14k•16•2•Updated Nov 15, 2024Nov 15, 2024
SWE-bench
Public
[ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?
benchmark software-engineering language-model
Python
•
MIT License
•344•2k•11•4•Updated Nov 11, 2024Nov 11, 2024
HELMET
Public
The HELMET Benchmark
Python
•
MIT License
•8•70•3•0•Updated Nov 5, 2024Nov 5, 2024
SimPO
Public
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
alignment large-language-models rlhf preference-alignment
Python
•
MIT License
•49•710•16•0•Updated Nov 4, 2024Nov 4, 2024
Edge-Pruning
Public
[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
Python
•
MIT License
•4•25•1•0•Updated Oct 31, 2024Oct 31, 2024
ProLong
Public
Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
Python
•
MIT License
•1•117•1•0•Updated Oct 30, 2024Oct 30, 2024
CharXiv
Public
[NeurIPS 2024] CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
benchmark machine-learning multimodal vision-language-model chart-understanding
Python
•
Apache License 2.0
•8•75•0•0•Updated Oct 20, 2024Oct 20, 2024
LESS
Public
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
data influence llama mistral data-selection llm instruction-tuning
Jupyter Notebook
•
MIT License
•32•369•13•1•Updated Oct 20, 2024Oct 20, 2024
unintentional-unalignment
Public
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Python
•
MIT License
•0•13•0•0•Updated Oct 17, 2024Oct 17, 2024
SimCSE
Public
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
nlp sentence-embeddings
Python
•
MIT License
•517•3.4k•1•0•Updated Oct 16, 2024Oct 16, 2024
ALCE
Public
[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627
Python
•
MIT License
•41•460•3•1•Updated Oct 9, 2024Oct 9, 2024
benign-data-breaks-safety
Public
Python
•0•21•0•0•Updated Oct 1, 2024Oct 1, 2024
NLProofS
Public
EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443
nlp machine-learning reasoning
Python
•
MIT License
•15•81•1•0•Updated Sep 15, 2024Sep 15, 2024
MQuAKE
Public
[EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Jupyter Notebook
•
MIT License
•8•102•8•0•Updated Sep 12, 2024Sep 12, 2024
AutoCompressors
Public
[EMNLP 2023] Adapting Language Models to Compress Long Contexts
Python
•20•276•4•0•Updated Sep 9, 2024Sep 9, 2024
WebShop
Public
[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
nlp language decision-making ml shopping rl web-based language-grounding rl-environment sim-to-real
Python
•
MIT License
•62•275•7•1•Updated Sep 6, 2024Sep 6, 2024
il-scaling-in-games
Public
Official code repo of "Scaling Laws for Imitation Learning in Single-Agent Games"
Python
•0•7•0•0•Updated Aug 14, 2024Aug 14, 2024
LM-Science-Tutor
Public
Python
•2•36•0•0•Updated Aug 6, 2024Aug 6, 2024
USACO
Public
Can Language Models Solve Olympiad Programming?
Python
•8•100•0•0•Updated Aug 2, 2024Aug 2, 2024
ELIZA-Transformer
Public
Representing Rule-based Chatbots with Transformers
Python
•
MIT License
•2•18•0•0•Updated Jul 16, 2024Jul 16, 2024
LitSearch
Public
[EMNLP 2024] A Retrieval Benchmark for Scientific Literature Search
Python
•
MIT License
•5•61•2•0•Updated Jul 10, 2024Jul 10, 2024
PTP
Public
Improving Language Understanding from Screenshots. Paper: https://arxiv.org/abs/2402.14073
Python
•
MIT License
•0•26•1•0•Updated Jul 9, 2024Jul 9, 2024
LLMBar
Public
[ICLR 2024] Evaluating Large Language Models at Evaluating Instruction Following
nlp evaluation llm
Python
•
MIT License
•8•116•0•0•Updated Jul 8, 2024Jul 8, 2024
CopyCat
Public
Python
•0•9•0•0•Updated Jun 25, 2024Jun 25, 2024
tree-of-thought-llm
Public
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
tree-search large-language-models llm prompting tree-of-thoughts
Python
•
MIT License
•448•4.8k•1•2•Updated Jun 22, 2024Jun 22, 2024
QuRating
Public
[ICML 2024] Selecting High-Quality Data for Training Language Models
Python
•10•145•3•0•Updated Jun 20, 2024Jun 20, 2024
CEPE
Public
[ACL 2024] Long-Context Language Modeling with Parallel Encodings
Python
•
MIT License
•9•143•2•0•Updated Jun 13, 2024Jun 13, 2024
Heuristic-Core
Public
[ACL 2024] The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models - https://arxiv.org/abs/2403.03942
Python
•
MIT License
•0•9•0•0•Updated Jun 4, 2024Jun 4, 2024
c-sts
Public
[EMNLP 2023] C-STS: Conditional Semantic Textual Similarity
Python
•7•66•3•0•Updated May 23, 2024May 23, 2024
TransformerPrograms
Public
[NeurIPS 2023] Learning Transformer Programs
Python
•22•157•2•0•Updated May 21, 2024May 21, 2024