@inproceedings{tran-etal-2025-leaf,
title = "{LEAF}: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models",
author = "Tran, Hieu and
Wang, Junda and
Ting, Yujan and
Yu, Hong and
Huang, Weijing and
Chen, Terrence",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.23/",
doi = "10.18653/v1/2025.emnlp-industry.23",
pages = "338--363",
ISBN = "979-8-89176-333-3",
abstract = "Large language models (LLMs) often struggle with factual accuracy in knowledge-intensive domains like healthcare. We introduce LEAF (Learning and Evaluation Augmented by Fact-Checking), a framework for improving LLM factuality in medical question answering. LEAF comprises three components: (1) \textbf{RAFE}, a robust fact-checking system using open-source LLMs and domain-specific retrieval to evaluate response accuracy; (2) \textbf{Fact-Check-then-RAG}, which leverages fact-checking results to guide retrieval without parameter updates; and (3) \textbf{Learning from Fact Check}, enabling self-training through supervised fine-tuning or preference-based learning using fact-checking as pseudo-labels. Experimental results show that RAFE outperforms Factcheck-GPT in detecting inaccuracies, Fact-Check-then-RAG effectively corrects errors, and Learning from Fact Check improves performance without labeled data. In a real-world healthcare deployment with proprietary medical documents, LEAF achieved an 83{\%} improvement in factuality scores, demonstrating practical applicability for adapting general-purpose LLMs to organization-specific knowledge. Our framework provides a scalable solution for industrial applications requiring high factual accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2025-leaf">
<titleInfo>
<title>LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junda</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujan</namePart>
<namePart type="family">Ting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terrence</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Large language models (LLMs) often struggle with factual accuracy in knowledge-intensive domains like healthcare. We introduce LEAF (Learning and Evaluation Augmented by Fact-Checking), a framework for improving LLM factuality in medical question answering. LEAF comprises three components: (1) RAFE, a robust fact-checking system using open-source LLMs and domain-specific retrieval to evaluate response accuracy; (2) Fact-Check-then-RAG, which leverages fact-checking results to guide retrieval without parameter updates; and (3) Learning from Fact Check, enabling self-training through supervised fine-tuning or preference-based learning using fact-checking as pseudo-labels. Experimental results show that RAFE outperforms Factcheck-GPT in detecting inaccuracies, Fact-Check-then-RAG effectively corrects errors, and Learning from Fact Check improves performance without labeled data. In a real-world healthcare deployment with proprietary medical documents, LEAF achieved an 83% improvement in factuality scores, demonstrating practical applicability for adapting general-purpose LLMs to organization-specific knowledge. Our framework provides a scalable solution for industrial applications requiring high factual accuracy.</abstract>
<identifier type="citekey">tran-etal-2025-leaf</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-industry.23</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.23/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>338</start>
<end>363</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
%A Tran, Hieu
%A Wang, Junda
%A Ting, Yujan
%A Yu, Hong
%A Huang, Weijing
%A Chen, Terrence
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F tran-etal-2025-leaf
%X Large language models (LLMs) often struggle with factual accuracy in knowledge-intensive domains like healthcare. We introduce LEAF (Learning and Evaluation Augmented by Fact-Checking), a framework for improving LLM factuality in medical question answering. LEAF comprises three components: (1) RAFE, a robust fact-checking system using open-source LLMs and domain-specific retrieval to evaluate response accuracy; (2) Fact-Check-then-RAG, which leverages fact-checking results to guide retrieval without parameter updates; and (3) Learning from Fact Check, enabling self-training through supervised fine-tuning or preference-based learning using fact-checking as pseudo-labels. Experimental results show that RAFE outperforms Factcheck-GPT in detecting inaccuracies, Fact-Check-then-RAG effectively corrects errors, and Learning from Fact Check improves performance without labeled data. In a real-world healthcare deployment with proprietary medical documents, LEAF achieved an 83% improvement in factuality scores, demonstrating practical applicability for adapting general-purpose LLMs to organization-specific knowledge. Our framework provides a scalable solution for industrial applications requiring high factual accuracy.
%R 10.18653/v1/2025.emnlp-industry.23
%U https://aclanthology.org/2025.emnlp-industry.23/
%U https://doi.org/10.18653/v1/2025.emnlp-industry.23
%P 338-363
Markdown (Informal)
[LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models](https://aclanthology.org/2025.emnlp-industry.23/) (Tran et al., EMNLP 2025)
ACL