@inproceedings{filice-etal-2025-generate,
title = "Generate but Verify: Answering with Faithfulness in {RAG}-based Question Answering",
author = "Filice, Simone and
Haramaty, Elad and
Horowitz, Guy and
Karnin, Zohar and
Lewin-Eytan, Liane and
Shtoff, Alex",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.56/",
pages = "1017--1037",
ISBN = "979-8-89176-298-5",
abstract = "Retrieval-Augmented Generation (RAG) enhances LLMs by grounding answers in retrieved passages, which is key in factual Question Answering. However, generated answers may still be unfaithful to the passages, either due to retrieval or generation errors. Many RAG downstream applications rely on assessing answer faithfulness for applying fallback strategies, yet address it implicitly, without a consistent evaluation methodology. We introduce the task of Answering with Faithfulness (AwF), which brings faithfulness prediction to the forefront, explicitly coupling it with answer generation. We define variants of the precision and recall metrics tailored to this task, facilitating direct evaluation and comparison of different AwF methods.We then demonstrate, both theoretically and empirically, that for RAG applications using AwF as a sub-procedure, an improvement to the AwF metrics translates to an improvement to the downstream performance. This results in improved performance for recently published results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="filice-etal-2025-generate">
<titleInfo>
<title>Generate but Verify: Answering with Faithfulness in RAG-based Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Filice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elad</namePart>
<namePart type="family">Haramaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Horowitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zohar</namePart>
<namePart type="family">Karnin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liane</namePart>
<namePart type="family">Lewin-Eytan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Shtoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) enhances LLMs by grounding answers in retrieved passages, which is key in factual Question Answering. However, generated answers may still be unfaithful to the passages, either due to retrieval or generation errors. Many RAG downstream applications rely on assessing answer faithfulness for applying fallback strategies, yet address it implicitly, without a consistent evaluation methodology. We introduce the task of Answering with Faithfulness (AwF), which brings faithfulness prediction to the forefront, explicitly coupling it with answer generation. We define variants of the precision and recall metrics tailored to this task, facilitating direct evaluation and comparison of different AwF methods.We then demonstrate, both theoretically and empirically, that for RAG applications using AwF as a sub-procedure, an improvement to the AwF metrics translates to an improvement to the downstream performance. This results in improved performance for recently published results.</abstract>
<identifier type="citekey">filice-etal-2025-generate</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.56/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1017</start>
<end>1037</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generate but Verify: Answering with Faithfulness in RAG-based Question Answering
%A Filice, Simone
%A Haramaty, Elad
%A Horowitz, Guy
%A Karnin, Zohar
%A Lewin-Eytan, Liane
%A Shtoff, Alex
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F filice-etal-2025-generate
%X Retrieval-Augmented Generation (RAG) enhances LLMs by grounding answers in retrieved passages, which is key in factual Question Answering. However, generated answers may still be unfaithful to the passages, either due to retrieval or generation errors. Many RAG downstream applications rely on assessing answer faithfulness for applying fallback strategies, yet address it implicitly, without a consistent evaluation methodology. We introduce the task of Answering with Faithfulness (AwF), which brings faithfulness prediction to the forefront, explicitly coupling it with answer generation. We define variants of the precision and recall metrics tailored to this task, facilitating direct evaluation and comparison of different AwF methods.We then demonstrate, both theoretically and empirically, that for RAG applications using AwF as a sub-procedure, an improvement to the AwF metrics translates to an improvement to the downstream performance. This results in improved performance for recently published results.
%U https://aclanthology.org/2025.ijcnlp-long.56/
%P 1017-1037
Markdown (Informal)
[Generate but Verify: Answering with Faithfulness in RAG-based Question Answering](https://aclanthology.org/2025.ijcnlp-long.56/) (Filice et al., IJCNLP-AACL 2025)
ACL
- Simone Filice, Elad Haramaty, Guy Horowitz, Zohar Karnin, Liane Lewin-Eytan, and Alex Shtoff. 2025. Generate but Verify: Answering with Faithfulness in RAG-based Question Answering. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 1017–1037, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.