Advancing LLM Reasoning Generalists with Preference Trees
Research paper by Lifan Yuan and collaborators. Published 2024-04-02. Topics: large language models (LLMs), Mistral-7B, CodeLlama-70B, reasoning, fine-tuning.
Resource information
- Authors
- Lifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding, Xingyao Wang, Jia Deng, Boji Shan, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, Maosong Sun
- Research topics
- large language models (LLMs), Mistral-7B, CodeLlama-70B, reasoning, fine-tuning, UltraInteract, benchmarking, LeetCode, TheoremQA, preference learning, preference tree, reasoning chains
- Publication date
- 2024-04-02
- Publication
- arXiv
- Last record update
- Nov 3, 2026