Papers with reward quality
LiTS: A Modular Framework for LLM Tree Search (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing tree search methods are task-specific and require substantial reimplementation effort when adapting to new domains. |
| Approach: | They propose a Python framework for LLM reasoning via tree search that decomposes tree search into three reusable components that plug into algorithms like MCTS and BFS. |
| Outcome: | The proposed framework decomposes tree search into three reusable components that plug into algorithms like MCTS and BFS. |
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang
| Challenge: | Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. |
| Approach: | They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data. |
| Outcome: | The proposed framework transforms user-generated content into user queries and generates responses from the policy model. |