#
Starred repositories
Retrieval and Retrieval-augmented LLMs
Code for paper: [ICLR 2025] Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Code and data for the Chain-of-Draft (CoD) paper
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Code and Slides
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
This repository contains code for the paper Direct Preference Optimization with an Offset (ODPO).
Train transformer language models with reinforcement learning.
Code of "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model"
[EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024
[NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
Localizing Memorized Sequences in Language Models
Understanding the interplay between memorization and generalization in neural networks, featuring MAT, a learning algorithm to enhance robustness by mitigating spurious correlations.
A framework for few-shot evaluation of language models.
Evaluation of the Cross-Lingual Knowledge Alignment in LLMs