TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

[NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.

A bibliography and survey of the papers surrounding o1

DataComp for Language Models

RewardBench: the first evaluation tool for reward models.

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"

Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"

Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…

Fuzzy String Matching in Python

Quality information extraction at web scale.

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"

[ACL 2023] Reasoning with Language Model Prompting: A Survey

Instruct-tune LLaMA on consumer hardware

Code for the ACL-2022 paper "Knowledge Neurons in Pretrained Transformers"

Locating and editing factual associations in GPT (NeurIPS 2022)

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

The open-sourced Python toolbox for backdoor attacks and defenses.

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"

Pytorch implementation of Deep Variational Information Bottleneck