@inproceedings{russo-etal-2025-face,
title = "Face the Facts! Evaluating {RAG}-based Pipelines for Professional Fact-Checking",
author = "Russo, Daniel and
Menini, Stefano and
Staiano, Jacopo and
Guerini, Marco",
editor = "Flek, Lucie and
Narayan, Shashi and
Phương, L{\^e} Hồng and
Pei, Jiahuan",
booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.inlg-main.50/",
pages = "846--865",
abstract = "Natural Language Processing and Generation systems have recently shown the potential to complement and streamline the costly and time-consuming job of professional fact-checkers. In this work, we lift several constraints of current state-of-the-art pipelines for automated fact-checking based on the Retrieval-Augmented Generation (RAG) paradigm. Our goal is to benchmark, following professional fact-checking practices, RAG-based methods for the generation of verdicts - i.e., short texts discussing the veracity of a claim - evaluating them on stylistically complex claims and heterogeneous, yet reliable, knowledge bases. Our findings show a complex landscape, where, for example, LLM-based retrievers outperform other retrieval techniques, though they still struggle with heterogeneous knowledge bases; larger models excel in verdict faithfulness, while smaller models provide better context adherence, with human evaluations favouring zero-shot and one-shot approaches for informativeness, and fine-tuned models for emotional alignment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="russo-etal-2025-face">
<titleInfo>
<title>Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Russo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Menini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Staiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Guerini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="family">Narayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lê</namePart>
<namePart type="given">Hồng</namePart>
<namePart type="family">Phương</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural Language Processing and Generation systems have recently shown the potential to complement and streamline the costly and time-consuming job of professional fact-checkers. In this work, we lift several constraints of current state-of-the-art pipelines for automated fact-checking based on the Retrieval-Augmented Generation (RAG) paradigm. Our goal is to benchmark, following professional fact-checking practices, RAG-based methods for the generation of verdicts - i.e., short texts discussing the veracity of a claim - evaluating them on stylistically complex claims and heterogeneous, yet reliable, knowledge bases. Our findings show a complex landscape, where, for example, LLM-based retrievers outperform other retrieval techniques, though they still struggle with heterogeneous knowledge bases; larger models excel in verdict faithfulness, while smaller models provide better context adherence, with human evaluations favouring zero-shot and one-shot approaches for informativeness, and fine-tuned models for emotional alignment.</abstract>
<identifier type="citekey">russo-etal-2025-face</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.50/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>846</start>
<end>865</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking
%A Russo, Daniel
%A Menini, Stefano
%A Staiano, Jacopo
%A Guerini, Marco
%Y Flek, Lucie
%Y Narayan, Shashi
%Y Phương, Lê Hồng
%Y Pei, Jiahuan
%S Proceedings of the 18th International Natural Language Generation Conference
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F russo-etal-2025-face
%X Natural Language Processing and Generation systems have recently shown the potential to complement and streamline the costly and time-consuming job of professional fact-checkers. In this work, we lift several constraints of current state-of-the-art pipelines for automated fact-checking based on the Retrieval-Augmented Generation (RAG) paradigm. Our goal is to benchmark, following professional fact-checking practices, RAG-based methods for the generation of verdicts - i.e., short texts discussing the veracity of a claim - evaluating them on stylistically complex claims and heterogeneous, yet reliable, knowledge bases. Our findings show a complex landscape, where, for example, LLM-based retrievers outperform other retrieval techniques, though they still struggle with heterogeneous knowledge bases; larger models excel in verdict faithfulness, while smaller models provide better context adherence, with human evaluations favouring zero-shot and one-shot approaches for informativeness, and fine-tuned models for emotional alignment.
%U https://aclanthology.org/2025.inlg-main.50/
%P 846-865
Markdown (Informal)
[Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking](https://aclanthology.org/2025.inlg-main.50/) (Russo et al., INLG 2025)
ACL