Asap7772 / understanding-rlhfLinks
Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Our new work finds that approaches employing on-policy sampling or negative gradients outperform offline, maximum likelihood objectives.
☆32Updated last year
Alternatives and similar repositories for understanding-rlhf
Users that are interested in understanding-rlhf are comparing it to the libraries listed below
Sorting:
- ☆103Updated last year
- Dateset Reset Policy Optimization☆31Updated last year
- Directional Preference Alignment☆57Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- Self-Supervised Alignment with Mutual Information☆21Updated last year
- The repository contains code for Adaptive Data Optimization☆26Updated 10 months ago
- ☆152Updated 11 months ago
- CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)☆71Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆66Updated 6 months ago
- Sotopia-RL: Reward Design for Social Intelligence☆43Updated 2 months ago
- NeurIPS 2024 tutorial on LLM Inference☆47Updated 10 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 6 months ago
- RL algorithm: Advantage induced policy alignment☆65Updated 2 years ago
- ☆33Updated 9 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆64Updated 6 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆57Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated last year
- ☆25Updated 7 months ago
- Reinforcing General Reasoning without Verifiers☆91Updated 4 months ago
- Verlog: A Multi-turn RL framework for LLM agents☆63Updated 2 weeks ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆65Updated 8 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆13Updated 2 months ago
- ☆20Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆59Updated last year
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆22Updated last week
- ☆100Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated last year
- Natural Language Reinforcement Learning☆98Updated 2 months ago