14 papers
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
Yubo Li, Ramayya Krishnan, Rema Padman
When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with conservative defa…
Auditing Institutional Heterogeneity for Generative AI in Patient Education: A Large-Scale Study of 102 US Transplant Handbooks
Yubo Li, Rema Padman, Ramayya Krishnan
Health systems are rapidly deploying generative AI assistants that answer patient questions from institution-authored education materials, on the premise that grounding in local co…
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
Yubo Li, Ramayya Krishnan, Rema Padman
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find…
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG
Yubo Li, Rema Padman, Ramayya Krishnan
A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depending on which source it retrie…
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
Yubo Li, Ramayya Krishnan, Rema Padman
Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We intr…
Consistency of Large Reasoning Models Under Multi-Turn Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underex…