11 papers
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
Xu Shen, Zhen Tan, Song Wang +4
Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual…
A Survey of Scaling in Large Language Model Reasoning
Zihan Chen, Song Wang, Zhen Tan +6
The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. How…
Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
Zhen Tan, Chengshuai Zhao, Song Wang +3
Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent ad…
AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
Song Wang, Zhen Tan, Zihan Chen +3
Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existin…
Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks
Song Wang, Zhenyu Lei, Zhen Tan +4
Nearly one in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder, underscoring the urgency of…
Learning from Diverse Reasoning Paths with Routing and Collaboration
Zhenyu Lei, Zhen Tan, Song Wang +4
Advances in large language models (LLMs) significantly enhance reasoning capabilities but their deployment is restricted in resource-constrained scenarios. Knowledge distillation a…