satrams / rent-rlLinks
RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.
☆20Updated last week
Alternatives and similar repositories for rent-rl
Users that are interested in rent-rl are comparing it to the libraries listed below
Sorting:
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated last month
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆25Updated last year
- A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models☆23Updated 6 months ago
- Self-Supervised Alignment with Mutual Information☆19Updated last year
- Analyzing LLM Alignment via Token distribution shift☆16Updated last year
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆38Updated last year
- Directional Preference Alignment☆57Updated 8 months ago
- ☆13Updated 10 months ago
- ☆59Updated 9 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 5 months ago
- [ACL 2024 Findings] CriticBench: Benchmarking LLMs for Critique-Correct Reasoning☆25Updated last year
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 5 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆73Updated 2 weeks ago
- ☆17Updated last year
- Evaluate the Quality of Critique☆35Updated last year
- ☆18Updated 9 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆40Updated 8 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆33Updated 9 months ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆50Updated this week
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 5 months ago
- AbstainQA, ACL 2024☆25Updated 7 months ago
- ☆30Updated last year
- ☆22Updated 11 months ago
- Codebase for Instruction Following without Instruction Tuning☆34Updated 8 months ago
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆24Updated 3 weeks ago
- ☆15Updated last month
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆32Updated 8 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆22Updated 3 months ago
- ☆40Updated last year
- instruction-following benchmark for large reasoning models☆31Updated last week