Hallucination Detection-Guided Preference Optimization for Clinical Summarization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Seethakantha, Shamanth Kuthpadi, Thai, Dung Ngoc, Gudi, Vara Prasad, Tiwari, Simran, Matar, Rami, Mitra, Avijit, Zhao, Wenlong, McCallum, Andrew, Salloum, Wael
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917554771984384
author Seethakantha, Shamanth Kuthpadi
Thai, Dung Ngoc
Gudi, Vara Prasad
Tiwari, Simran
Matar, Rami
Mitra, Avijit
Zhao, Wenlong
McCallum, Andrew
Salloum, Wael
author_facet Seethakantha, Shamanth Kuthpadi
Thai, Dung Ngoc
Gudi, Vara Prasad
Tiwari, Simran
Matar, Rami
Mitra, Avijit
Zhao, Wenlong
McCallum, Andrew
Salloum, Wael
contents Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce \itermodelfull (\itermodel), an inference-time method that leverages hallucination detectors to guide iterative summary revisions toward factual corrections. Building on this, we propose \itermodel for Preference Learning (\model), which converts detector-guided refinement trajectories into preference pairs for model finetuning. Extensive experiments show that our methods substantially reduce hallucinations for Llama and Gemma models in summarizing real-world clinical notes from \MimicIV. For example, \itermodel reduces 24\% and \model reduces 48\% hallucinations in Llama-3.1-8B-Instruct. Importantly, both methods preserve summary fluency, coherence, and relevance according to human expert and LLM-Jury evaluations. Together, these results demonstrate that detection-informed refinement and preference learning offer an automated solution for improving factual faithfulness in clinical summarization.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28910
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hallucination Detection-Guided Preference Optimization for Clinical Summarization
Seethakantha, Shamanth Kuthpadi
Thai, Dung Ngoc
Gudi, Vara Prasad
Tiwari, Simran
Matar, Rami
Mitra, Avijit
Zhao, Wenlong
McCallum, Andrew
Salloum, Wael
Computation and Language
Artificial Intelligence
Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce \itermodelfull (\itermodel), an inference-time method that leverages hallucination detectors to guide iterative summary revisions toward factual corrections. Building on this, we propose \itermodel for Preference Learning (\model), which converts detector-guided refinement trajectories into preference pairs for model finetuning. Extensive experiments show that our methods substantially reduce hallucinations for Llama and Gemma models in summarizing real-world clinical notes from \MimicIV. For example, \itermodel reduces 24\% and \model reduces 48\% hallucinations in Llama-3.1-8B-Instruct. Importantly, both methods preserve summary fluency, coherence, and relevance according to human expert and LLM-Jury evaluations. Together, these results demonstrate that detection-informed refinement and preference learning offer an automated solution for improving factual faithfulness in clinical summarization.
title Hallucination Detection-Guided Preference Optimization for Clinical Summarization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.28910