MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwok, Tung Sum Thomas, Qian, Qian, Lin, Xiaofeng, Zhang, Dongxu, Han, Jun, Yang, Zhichao, Hill, Davin, Soliman, Tamer, Batra, Sanjit Singh, Tillman, Robert, Cheng, Guang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914532409999360
author Kwok, Tung Sum Thomas
Qian, Qian
Lin, Xiaofeng
Zhang, Dongxu
Han, Jun
Yang, Zhichao
Hill, Davin
Soliman, Tamer
Batra, Sanjit Singh
Tillman, Robert
Cheng, Guang
author_facet Kwok, Tung Sum Thomas
Qian, Qian
Lin, Xiaofeng
Zhang, Dongxu
Han, Jun
Yang, Zhichao
Hill, Davin
Soliman, Tamer
Batra, Sanjit Singh
Tillman, Robert
Cheng, Guang
contents Large Language Models exhibit strong reasoning and semantic understanding capabilities but often hallucinate in domains that require expert knowledge, among which fabrications, the generation of factually incorrect yet fluent statements, pose the greatest risk in medical contexts. Existing medical hallucination datasets inadequately capture fabrication phenomena due to limited fabrication coverage, stylistic disparities between human and LLM-authored texts, and distributional drift during hallucinated sample synthesis. To address this, we propose a data-centric pipeline to generate realistic and word-level fabrications that preserve syntactic and stylistic fidelity while introducing subtle factual deviations, resulting in MedFabric. Building upon this dataset, we introduce ETHER, a modular word-level fabrication detector integrating Text2Table Decomposition, Word Masking and Filling and Hybrid Sentence Pair Evaluation to enhance factual alignment. Empirical results demonstrate that MedFabric outperforms state-of-the-art detectors by over 15% on word-level fabrication benchmarks while maintaining consistent performance across structural similarities, offering a comprehensive framework for reliable and domain-specific factuality detection.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04180
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs
Kwok, Tung Sum Thomas
Qian, Qian
Lin, Xiaofeng
Zhang, Dongxu
Han, Jun
Yang, Zhichao
Hill, Davin
Soliman, Tamer
Batra, Sanjit Singh
Tillman, Robert
Cheng, Guang
Computation and Language
Artificial Intelligence
Large Language Models exhibit strong reasoning and semantic understanding capabilities but often hallucinate in domains that require expert knowledge, among which fabrications, the generation of factually incorrect yet fluent statements, pose the greatest risk in medical contexts. Existing medical hallucination datasets inadequately capture fabrication phenomena due to limited fabrication coverage, stylistic disparities between human and LLM-authored texts, and distributional drift during hallucinated sample synthesis. To address this, we propose a data-centric pipeline to generate realistic and word-level fabrications that preserve syntactic and stylistic fidelity while introducing subtle factual deviations, resulting in MedFabric. Building upon this dataset, we introduce ETHER, a modular word-level fabrication detector integrating Text2Table Decomposition, Word Masking and Filling and Hybrid Sentence Pair Evaluation to enhance factual alignment. Empirical results demonstrate that MedFabric outperforms state-of-the-art detectors by over 15% on word-level fabrication benchmarks while maintaining consistent performance across structural similarities, offering a comprehensive framework for reliable and domain-specific factuality detection.
title MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.04180