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.
☆32Apr 20, 2024Updated last year
Alternatives and similar repositories for understanding-rlhf
Users that are interested in understanding-rlhf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Code Release for "Training a Generally Curious Agent"☆45May 18, 2025Updated 10 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Oct 3, 2024Updated last year
- ☆25Apr 3, 2025Updated last year
- A simple and easy to use implementation of the soft actor-critic algorithm.☆15Sep 2, 2022Updated 3 years ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Apr 17, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Counterfactual Evaluation and Learning for Interactive Systems: Foundations, Implementations, and Recent Advances☆12Aug 14, 2022Updated 3 years ago
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆29Mar 1, 2025Updated last year
- Official repo for Offline RL for Online RL☆19Oct 14, 2023Updated 2 years ago
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Feb 22, 2024Updated 2 years ago
- ☆10Nov 17, 2022Updated 3 years ago
- ☆35Apr 12, 2024Updated 2 years ago
- Code for Diagnosing Bottlenecks in Deep Q-learning. Contains implementations of tabular environments plus solvers.☆18May 14, 2019Updated 6 years ago
- Models for explainable recommendation.☆12Jan 19, 2024Updated 2 years ago
- ☆15Oct 4, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- (NeurIPS '22) LISA: Learning Interpretable Skill Abstractions - A framework for unsupervised skill learning using Imitation☆29Feb 22, 2023Updated 3 years ago
- Optim4RL is a Jax framework of learning to optimize for reinforcement learning.☆28Nov 27, 2024Updated last year
- Training tiny models to prove hard theorems☆72Mar 5, 2026Updated last month
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆19Aug 17, 2025Updated 7 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆62Aug 30, 2024Updated last year
- ☆12Jul 4, 2024Updated last year
- ☆24Feb 16, 2022Updated 4 years ago
- ☆16Feb 22, 2025Updated last year
- Website for release of TellMeWhy dataset for why question answering☆14Nov 11, 2022Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Drop-in environment replacements that make your RL algorithm train faster.☆22Jun 19, 2024Updated last year
- ☆12Nov 15, 2022Updated 3 years ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆48Jan 19, 2024Updated 2 years ago
- This repo explores how AMR to address tasks difficult for LLMs☆13Jan 15, 2024Updated 2 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Sep 12, 2023Updated 2 years ago
- ☆21Apr 3, 2026Updated last week
- ☆99Jun 27, 2024Updated last year
- The official implementation of Self-Exploring Language Models (SELM)☆63Jun 4, 2024Updated last year
- Code to accompany the paper "The Information Geometry of Unsupervised Reinforcement Learning"☆20Oct 6, 2021Updated 4 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Self-Supervised Alignment with Mutual Information☆20May 24, 2024Updated last year
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆65Oct 24, 2025Updated 5 months ago
- ☆25Jan 17, 2025Updated last year
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆32Jan 7, 2026Updated 3 months ago
- Fork of Flame repo for training of some new stuff in development☆19Updated this week
- ☆12Dec 22, 2021Updated 4 years ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94May 23, 2023Updated 2 years ago