作者位次 #2/9ACL 2026Poster· Natural Language Processing
Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
Yan Liu · Feng Zhang · Zhanyu Ma · Jun Xu · Jiuchong Gao · Jinghua Hao · Renqing He · Han Liu · Yangdong Deng
摘要
High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequence, lacking an intrinsic mechanism to quantify step-wise information gain. Th...