AI Paper Atlas

Research map / Large language models / AI and society

MHB: Medical Hallucination Benchmark for Large Language Models in Complex Clinical Tasks

Jianrong Lu, Junwei Liu, Xingyun Zheng, Minghui Yang, Jian Wang, Ping Wang, Yechao Zhang

AAAI 2026 · Large language models › AI and society · approach: Data commons and human baselines

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
inject adversarial hallucination traps into dialogues and report questionsEvaluated LLMs · MHB-Combinedhallucination rate: 29.1% best (Claude-4-Sonnet) to 59.0% worstHurt
non-existent entity trap (A1) in dialogueMost evaluated LLMs · MHB-Dialoguehallucination rateHurt
source fabrication trap (D2)Most evaluated LLMs · MHB-Dialoguehallucination rateHurt
incorrect factual claim trap (A3) in report questionsQwen, GPT · MHB-Reporthallucination rateHurt
temporal obsoletion traps (cluster E)GPT, Llama · MHB-Reporthallucination rateHurt
diagnostic misinterpretation (C3) and source fabrication (D2) trapsEvaluated LLMs · MHB-Combinedhallucination rateHurt
model choice: Claude vs Llama on dialogueClaude-4-Sonnet vs Llama-4-Scout · MHB-Dialoguehallucination rate: 0.793 -> 0.165Improved
ranking changes between dialogue and report tasksGemini 2.5-Pro · MHB-Report vs MHB-Dialoguehallucination rate: 0.357 (dialogue) vs 0.323 (report)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy