Tools for checking ACL paper submissions

Repository for XLM-T, a framework for evaluating multilingual language models on Twitter data

A library for mechanistic interpretability of GPT-style language models

A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enabling layer-wise analysis of hidden states and predictions.

PAIR.withgoogle.com and friend's work on interpretability methods

Simple RL training for reasoning

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Scripts for fine-tuning Llama2 via SFT and DPO.

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

FeedbackQA: Improving Question Answering Post-Deployment with Interactive Feedback

awesome SAE papers

A simple and elegant Jekyll theme for an academic personal homepage

Evaluating Cross-lingual Sentence Representations

Explaining ML models using LLMs

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…

Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models. Paper: https://arxiv.org/pdf/2411.02448

DL Backtrace is a new explainablity technique for deep learning models that works for any modality and model type.

code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models

ReadMe++: A Multi-domain Multilingual Dataset for Readability Assessment

Generative Judge for Evaluating Alignment

Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/

Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"

Code for running experiments as well as the dataset DynamicQA

Find and fix bugs in natural language machine learning models using adaptive testing.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.