VERI-DPO: Evidence-Aware Alignment for Clinical Summarization via Claim Verification and Direct Preference Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Weixin, Ni, Congning, Song, Qingyuan, Rose, Susannah L., Symons, Christopher, Kantarcioglu, Murat, Malin, Bradley A., Yin, Zhijun
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908878948532224
author Liu, Weixin
Ni, Congning
Song, Qingyuan
Rose, Susannah L.
Symons, Christopher
Kantarcioglu, Murat
Malin, Bradley A.
Yin, Zhijun
author_facet Liu, Weixin
Ni, Congning
Song, Qingyuan
Rose, Susannah L.
Symons, Christopher
Kantarcioglu, Murat
Malin, Bradley A.
Yin, Zhijun
contents Brief Hospital Course (BHC) narratives must be clinically useful yet faithful to fragmented EHR evidence. LLM-based clinical summarizers still introduce unsupported statements, and alignment can encourage omissions ("say-less" degeneration). We introduce VERI-DPO, which uses claim verification to mine preferences and distill them into the summarizer with Direct Preference Optimization (DPO). On MIMIC-III-Ext-VeriFact-BHC (100 ICU patients; patient-level splits), we train a retrieval-augmented verifier to label claim-evidence pairs as Supported, Not Supported, or Not Addressed via a single-token format. The verifier scores sentence-level claims from sampled BHC candidates and aggregates margins into a coverage-aware utility to mine length-controlled, contradiction-anchored preference pairs. On held-out patients, verifier-mined preferences separate candidates by contradiction density, and VERI-DPO reduces Not Supported claim rates from 10.7% to 1.9% (local verifier judge) and from 11.6% to 6.4% (GPT-4o judge), while improving validity from 76.7% to 82.5% and maintaining informative length.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10494
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VERI-DPO: Evidence-Aware Alignment for Clinical Summarization via Claim Verification and Direct Preference Optimization
Liu, Weixin
Ni, Congning
Song, Qingyuan
Rose, Susannah L.
Symons, Christopher
Kantarcioglu, Murat
Malin, Bradley A.
Yin, Zhijun
Computation and Language
Machine Learning
Brief Hospital Course (BHC) narratives must be clinically useful yet faithful to fragmented EHR evidence. LLM-based clinical summarizers still introduce unsupported statements, and alignment can encourage omissions ("say-less" degeneration). We introduce VERI-DPO, which uses claim verification to mine preferences and distill them into the summarizer with Direct Preference Optimization (DPO). On MIMIC-III-Ext-VeriFact-BHC (100 ICU patients; patient-level splits), we train a retrieval-augmented verifier to label claim-evidence pairs as Supported, Not Supported, or Not Addressed via a single-token format. The verifier scores sentence-level claims from sampled BHC candidates and aggregates margins into a coverage-aware utility to mine length-controlled, contradiction-anchored preference pairs. On held-out patients, verifier-mined preferences separate candidates by contradiction density, and VERI-DPO reduces Not Supported claim rates from 10.7% to 1.9% (local verifier judge) and from 11.6% to 6.4% (GPT-4o judge), while improving validity from 76.7% to 82.5% and maintaining informative length.
title VERI-DPO: Evidence-Aware Alignment for Clinical Summarization via Claim Verification and Direct Preference Optimization
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2603.10494