8 papers
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…
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…
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…
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…
Role and Use of Race in AI/ML Models Related to Health
Martin C. Were, Ang Li, Bradley A. Malin +9
The role and use of race within health-related artificial intelligence and machine learning (AI/ML) models has sparked increasing attention and controversy. Despite the complexity…
Towards Statistical Factuality Guarantee for Large Vision-Language Models
Zhuohang Li, Chao Yan, Nicholas J. Jackson +4
Advancements in Large Vision-Language Models (LVLMs) have demonstrated promising performance in a variety of vision-language tasks involving image-conditioned free-form text genera…
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
Zhuohang Li, Jiaxin Zhang, Chao Yan +4
Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowle…