paper-with-me

Papers

Beyond Accuracy: Risk-Sensitive Evaluation of Hallucinated Medical Advice

2026-02-07 · Savan Doshi arxiv

Large language models are increasingly being used in patient-facing medical question answering, where hallucinated outputs can vary widely in potential harm. However, existing hallucination standards and evaluation metrics focus primarily on factual correctness, treating all errors as equally severe. This obscures clinically relevant failure modes, particularly when models generate unsupported but actionable medical language. We propose a risk-sensitive evaluation framework that quantifies hallucinations through the presence of risk-bearing language, including treatment directives, contraindications, urgency cues, and mentions of high-risk medications. Rather than assessing clinical correctness, our approach evaluates the potential impact of hallucinated content if acted upon. We further combine risk scoring with a relevance measure to identify high-risk, low-grounding failures. We apply this framework to three instruction-tuned language models using controlled patient-facing prompts designed as safety stress tests. Our results show that models with similar surface-level behavior exhibit substantially different risk profiles and that standard evaluation metrics fail to capture these distinctions. These findings highlight the importance of incorporating risk sensitivity into hallucination evaluation and suggest that evaluation validity is critically dependent on task and prompt design.

📄 PDF Abstract BibTeX arXiv:2602.07319

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Risk-Aware Robust Learning: Reducing Clinical Risk under Label Noise in Medical Image Classification

2026-04-26 · Maycon R. S. Pereira, Filipe R. Cordeiro arxiv

Noisy labels are a pervasive challenge in medical image classification, where annotation errors arise from inter-observer variability and diagnostic ambiguity. Although several noise-robust learning methods have been pro…

Medical Image ClassificationMedical Diagnosis

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts

2025-09-09 · Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng 외 arxiv

As large language models (LLMs) are adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitig…

Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI

2025-09-12 · Zihao Li, Weiwei Yi, Jiahong Chen arxiv

Hallucination in generative AI is often treated as a technical failure to produce factually correct output. Yet this framing underrepresents the broader significance of hallucinated content in language models, which may …

Beyond Chat: a Framework for LLMs as Human-Centered Support Systems

2025-09-25 · Zhiyin Zhou arxiv

Large language models are moving beyond transactional question answering to act as companions, coaches, mediators, and curators that scaffold human growth, decision-making, and well-being. This paper proposes a role-base…

Question Answering

SHARP: Social Harm Analysis via Risk Profiles for Measuring Inequities in Large Language Models

2026-01-29 · Alok Abhishek, Tushar Bandopadhyay, Lisa Erickson arxiv

Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to…