10 papers · 2 filters
CoRA: Confidence-Rationale Alignment for Reliable Chain-of-Thought Reasoning
Juming Xiong, Weixin Liu, Kevin Guo +9
Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be misleading when the accompanying CoT rationale is plausible yet incomplete or poorly…
It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
Kevin H. Guo, Chao Yan, Avinash Baidya +5
Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned duri…
Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization
Weixin Liu, Bowen Qu, Juming Xiong +3
Large language model (LLM) summarization systems may pass compact vector representations of private inputs to downstream retrieval, monitoring, audit, or analytic workflows. Even w…
MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models
Weixin Liu, Congning Ni, Shelagh A. Mulvaney +4
Large language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they appl…
CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
Kevin H. Guo, Chao Yan, Avinash Baidya +5
Medical large language model (LLM) evaluations rely on simplified, exam-style benchmarks that rarely reflect the ambiguity of real-world medical inquiries. We introduce the CLinica…
Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
Khizar Hussain, Bradley A. Malin, Zhijun Yin +2
As LLM-powered chatbots are increasingly deployed in mental health services, detecting hallucinations and omissions has become critical for user safety. However, state-of-the-art L…
Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses
Congning Ni, Sarvech Qadir, Bryan Steitz +14
Mental health concerns are often expressed outside clinical settings, including in high-distress help seeking, where safety-critical guidance may be needed. Consumer health informa…
Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability
Kevin H. Guo, Chao Yan, Avinash Baidya +5
Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Address…
Coverage-Controlled Preference Mining from Noisy Claim Verification for Evidence-Grounded Generation
Weixin Liu, Congning Ni, Qingyuan Song +4
Evidence-grounded generation produces summaries whose claims should be supported by supplied evidence, but claim-level verifiers provide noisy feedback and can reward models that s…
Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning
Juming Xiong, Kevin Guo, Congning Ni +7
Large language models (LLMs) can achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet they often generate unnecessarily long reasoning paths that incu…