FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Afzal, Anum, Vladika, Juraj, Matthes, Florian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908515416670208
author Afzal, Anum
Vladika, Juraj
Matthes, Florian
author_facet Afzal, Anum
Vladika, Juraj
Matthes, Florian
contents Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-checking techniques: Chain-of-Thought (CoT) Prompting and Natural Language Inference (NLI). Our experiments show that the fact-checking scores acquired through the Unanimous Voting of both techniques correlate best with Domain Expert Evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
Afzal, Anum
Vladika, Juraj
Matthes, Florian
Computation and Language
Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-checking techniques: Chain-of-Thought (CoT) Prompting and Natural Language Inference (NLI). Our experiments show that the fact-checking scores acquired through the Unanimous Voting of both techniques correlate best with Domain Expert Evaluation.
title FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
topic Computation and Language
url https://arxiv.org/abs/2509.02198