Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.11129 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913890797879296 |
|---|---|
| author | Garcia-Fernandez, Carlos Felipe, Luis Shotande, Monique Zitu, Muntasir Tripathi, Aakash Rasool, Ghulam Naqa, Issam El Rudrapatna, Vivek Valdes, Gilmer |
| author_facet | Garcia-Fernandez, Carlos Felipe, Luis Shotande, Monique Zitu, Muntasir Tripathi, Aakash Rasool, Ghulam Naqa, Issam El Rudrapatna, Vivek Valdes, Gilmer |
| contents | Large language models (LLMs) show promise in healthcare, but hallucinations remain a major barrier to clinical use. We present CHECK, a continuous-learning framework that integrates structured clinical databases with a classifier grounded in information theory to detect both factual and reasoning-based hallucinations. Evaluated on 1500 questions from 100 pivotal clinical trials, CHECK reduced LLama3.3-70B-Instruct hallucination rates from 31% to 0.3% - making an open source model state of the art. Its classifier generalized across medical benchmarks, achieving AUCs of 0.95-0.96, including on the MedQA (USMLE) benchmark and HealthBench realistic multi-turn medical questioning. By leveraging hallucination probabilities to guide GPT-4o's refinement and judiciously escalate compute, CHECK boosted its USMLE passing rate by 5 percentage points, achieving a state-of-the-art 92.1%. By suppressing hallucinations below accepted clinical error thresholds, CHECK offers a scalable foundation for safe LLM deployment in medicine and other high-stakes domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK Garcia-Fernandez, Carlos Felipe, Luis Shotande, Monique Zitu, Muntasir Tripathi, Aakash Rasool, Ghulam Naqa, Issam El Rudrapatna, Vivek Valdes, Gilmer Computation and Language Artificial Intelligence Large language models (LLMs) show promise in healthcare, but hallucinations remain a major barrier to clinical use. We present CHECK, a continuous-learning framework that integrates structured clinical databases with a classifier grounded in information theory to detect both factual and reasoning-based hallucinations. Evaluated on 1500 questions from 100 pivotal clinical trials, CHECK reduced LLama3.3-70B-Instruct hallucination rates from 31% to 0.3% - making an open source model state of the art. Its classifier generalized across medical benchmarks, achieving AUCs of 0.95-0.96, including on the MedQA (USMLE) benchmark and HealthBench realistic multi-turn medical questioning. By leveraging hallucination probabilities to guide GPT-4o's refinement and judiciously escalate compute, CHECK boosted its USMLE passing rate by 5 percentage points, achieving a state-of-the-art 92.1%. By suppressing hallucinations below accepted clinical error thresholds, CHECK offers a scalable foundation for safe LLM deployment in medicine and other high-stakes domains. |
| title | Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.11129 |