27 papers
DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories
Weixin Liu, Juming Xiong, Congning Ni +4
Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and la…
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
Chongyu Qu, Can Cui, Zhengyi Lu +8
Does every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In multimodal clinical oncology, diagnostic modalities follow a clinically manda…
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…
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…
RadOT-Eval: Auditable Structured-Evidence Transport for Radiology Report Evaluation
Weixin Liu, Juming Xiong, Yang Li +5
Automatic evaluation is critical for high-stakes text generation, where errors often involve omitted findings, hallucinated content, polarity reversals, location changes, uncertain…
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…