Princeton Natural Language Processing ORG

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

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

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

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

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

[NAACL 2021] A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

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

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

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

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

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

The HELMET Benchmark

[ICML 2024] Selecting High-Quality Data for Training Language Models

[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408

[EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674

[ACL 2024] Long-Context Language Modeling with Parallel Encodings

[NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

[NeurIPS 2023] Learning Transformer Programs

[NeurIPS 2024] CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535

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

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

Can Language Models Solve Olympiad Programming?

Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃

[EMNLP 2024] A Retrieval Benchmark for Scientific Literature Search

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

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

[EMNLP 2020] Keep CALM and Explore: Language Models for Action Generation in Text-based Games

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

[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".

EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering

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

[NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks

EMNLP 2022: Finding Dataset Shortcuts with Grammar Induction https://arxiv.org/abs/2210.11560

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

No description.

No description.

[ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering

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

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

[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790

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.

[NAACL 2024 Findings] Evaluation suite for the systematic evaluation of instruction selection methods.

[NAACL 2025] Representing Rule-based Chatbots with Transformers

[ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning

Repo for paper: Controllable Text Generation with Language Constraints

Safe Reinforcement Learning with Natural Language Constraints

Semantic Supervision: Enabling Generalization over Output Spaces

[ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games

MUX-PLMs: Pretraining LMs with Data Multiplexing

No description.

[ACL 2021] Self-Attention Networks Can Process Bounded Hierarchical Languages

No description.

Repository for the paper titled: "When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer"

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

No description.

Continual Memorization of Factoids in Large Language Models

Official code repo of "Scaling Laws for Imitation Learning in Single-Agent Games"

[NAACL 2021] Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents

NAACL'2021: Non-Parametric Few-Shot Learning for Word Sense Disambiguation

SemSup-XC: Semantic Supervision for Extreme Classification

[ACL 2024] The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models - https://arxiv.org/abs/2403.03942

Code release for Improving Dialog Systems for Negotiation with Personality Modeling.

No description.

Extracting rule-based descriptions of attention rules

[LaReL 2022] Towards an Enhanced, Faithful, and Adaptable Web Interaction Environment

SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers

No description.

A query language for programming (large) language models.

Framework for learning dialogue agents in a two-player game setting.

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Minimalistic gridworld package for OpenAI Gym

ICLR 2021: "Monte-Carlo Planning and Learning with Language Action Value Estimates"

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".

Semantic Supervision: Enabling Generalization over Output Spaces

No description.

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

Translating natural language questions to a structured query language