5 papers
When Is a Steerable Concept Representation Real? Measurement Confounds in a Cross-Family Audit of Neuroscience Parallels in LLMs
Yuqi Wu, Shengming Zhao, Jie Chen
Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lines, and cognitive maps. Thes…
TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance
Yuqi Wu, Shengming Zhao, Jie Chen
Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone canno…
WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis
Yuqi Wu, Guangya Wan, Jingjing Li +6
Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they often lack the structured clinical reasoning needed for reliable diagnos…
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning
Guangya Wan, Yuqi Wu, Hao Wang +3
Large Language Models (LLMs) have shown impressive reasoning capabilities, yet existing prompting methods face a critical trade-off: simple approaches often struggle with complex t…
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
Guangya Wan, Yuqi Wu, Jie Chen +1
Self-Consistency mitigates hallucinations in Large Language Models (LLMs) by sampling multiple reasoning paths,but it lacks a systematic approach to determine the optimal number of…