hkust-nlp / dart-mathLinks
[NeurIPS'24] Official code for *๐ฏDART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
โ114Updated 9 months ago
Alternatives and similar repositories for dart-math
Users that are interested in dart-math are comparing it to the libraries listed below
Sorting:
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"โ171Updated 4 months ago
- Repo of paper "Free Process Rewards without Process Labels"โ164Updated 6 months ago
- The official repository of the Omni-MATH benchmark.โ88Updated 9 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".โ107Updated 2 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scalingโ176Updated 2 months ago
- โ74Updated 10 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learningโ111Updated 5 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracyโ69Updated 9 months ago
- RL Scaling and Test-Time Scaling (ICML'25)โ111Updated 8 months ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied witโฆโ142Updated last year
- GenRM-CoT: Data release for verification rationalesโ65Updated 11 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.โ128Updated 6 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.โ68Updated 11 months ago
- โ207Updated 6 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineeringโ61Updated 10 months ago
- โ211Updated 7 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or reโฆโ37Updated last year
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. ๐งฎโจโ258Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisionโ123Updated last year
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluationsโ130Updated 5 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"โ229Updated 3 weeks ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".โ82Updated 8 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correctionโ82Updated 6 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.โ83Updated 4 months ago
- [ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scieโฆโ171Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejectionโ51Updated 11 months ago
- โ67Updated 5 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Styleโ62Updated 2 months ago
- โ51Updated 4 months ago
- Resources for the Enigmata Project.โ72Updated last month