9 papers
The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment
Tianyu Jia, Yue Fang, Hongxin Ding +6
Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive s…
EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
Hongxin Ding, Baixiang Huang, Yue Fang +6
Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre…
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
Hongxin Ding, Baixiang Huang, Yue Fang +8
Interactive medical questioning is essential in clinical consultations, where physicians must actively gather necessary patient information. Yet existing medical Large Language Mod…
GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models
Yue Fang, Weibin Liao, Yuxin Guo +8
Clinical reasoning over electronic health records (EHRs) is a fundamental yet challenging task in modern healthcare. While large language models (LLMs) offer a promising paradigm v…
The Tell-Tale Norm: Magnitude as a Signal for Reasoning Dynamics in Large Language Models
Jinyang Zhang, Hongxin Ding, Yue Fang +4
Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reasoning dynamics remains undere…
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
Zhibang Yang, Xinke Jiang, Rihong Qiu +8
Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, e…