liziniu / policy_optimization
Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)
☆23Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for policy_optimization
- Rewarded soups official implementation☆49Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆52Updated 2 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆14Updated 11 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆38Updated 9 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆46Updated this week
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆29Updated 3 months ago
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆49Updated 5 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆24Updated 8 months ago
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆20Updated 2 months ago
- 🌾 OAT: Online AlignmenT for LLMs☆23Updated this week
- An index of algorithms for reinforcement learning from human feedback (rlhf))☆87Updated 6 months ago
- ☆35Updated 9 months ago
- Direct preference optimization with f-divergences.☆11Updated this week
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆14Updated last month
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆39Updated 3 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆29Updated 8 months ago
- [NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$☆28Updated 2 weeks ago
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆38Updated 3 months ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆104Updated 4 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆102Updated 7 months ago
- ☆27Updated 8 months ago
- ☆20Updated 4 months ago
- Directional Preference Alignment☆49Updated last month
- Explore what LLMs are really leanring over SFT☆26Updated 7 months ago
- Dateset Reset Policy Optimization☆28Updated 6 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆77Updated 2 weeks ago
- code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning☆32Updated 7 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆46Updated 4 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆95Updated 2 months ago