yinyueqin / relative-preference-optimization
Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
☆24Updated last year
Alternatives and similar repositories for relative-preference-optimization:
Users that are interested in relative-preference-optimization are comparing it to the libraries listed below
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆36Updated 9 months ago
- ☆41Updated 2 weeks ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆29Updated 7 months ago
- ☆14Updated 2 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆60Updated 4 months ago
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆75Updated 8 months ago
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models☆67Updated last year
- A Survey on the Honesty of Large Language Models☆57Updated 4 months ago
- ☆60Updated this week
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆53Updated 3 weeks ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆23Updated 2 weeks ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆43Updated last week
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆66Updated 6 months ago
- Directional Preference Alignment☆57Updated 7 months ago
- This is the repo for our paper "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models"☆49Updated 5 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆64Updated 4 months ago
- M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆56Updated 4 months ago
- This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by g…☆34Updated 3 weeks ago
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆41Updated 6 months ago
- Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment☆68Updated last year
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆16Updated last year
- [NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$☆43Updated 6 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆42Updated 3 weeks ago
- ☆13Updated 9 months ago
- ☆44Updated 5 months ago
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆71Updated 2 years ago
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆51Updated 5 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆72Updated 5 months ago
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆62Updated this week