@inproceedings{liu-etal-2026-beyond-correctness,
title = "Beyond Correctness: A Framework for Analyzing Reasoning and Faithfulness of Multi-hop Question Answering",
author = "Liu, Jiyuan and
Xie, Yi and
Rao, Yanghui and
Wang, Fu Lee and
Yu, Jianxing and
Qing, Li",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.135/",
pages = "2628--2648",
ISBN = "979-8-89176-444-6",
abstract = "Diagnosing the root causes of failures in Retrieval-Augmented Generation (RAG) is challenging, as current evaluations often conflate logical reasoning errors with the failure to adhere to retrieved context. To address this, we propose **ReFa**, a framework inspired by Structural Causal Models to explicitly disentangle *Reasoning* from *Faithfulness*. Through this lens, we characterize two distinct failure modes: the **{`}Fool'**, representing a deficiency in logical reasoning, and the **{`}Lazy'**, representing a lapse in faithfulness where the model defaults to parametric priors. To operationalize this diagnosis, we introduce Dual Reasoning Chain Editing, a mechanism that constructs controlled proxy chains to isolate reasoning structure from evidence faithfulness. We apply this method on **ReFaBench**, a novel benchmark constructed in this work featuring factual, counterfactual, and knowledge-conflicting scenarios. Furthermore, we propose **ReFa-DPO**, a decoupled preference optimization strategy that leverages these proxies to target specific failure patterns. Experimental results demonstrate that **ReFa-DPO** enhances robustness, particularly in mitigating parametric interference, by simultaneously enhancing both contextual faithfulness and reasoning capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-beyond-correctness">
<titleInfo>
<title>Beyond Correctness: A Framework for Analyzing Reasoning and Faithfulness of Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghui</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxing</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Qing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Diagnosing the root causes of failures in Retrieval-Augmented Generation (RAG) is challenging, as current evaluations often conflate logical reasoning errors with the failure to adhere to retrieved context. To address this, we propose **ReFa**, a framework inspired by Structural Causal Models to explicitly disentangle *Reasoning* from *Faithfulness*. Through this lens, we characterize two distinct failure modes: the **‘Fool’**, representing a deficiency in logical reasoning, and the **‘Lazy’**, representing a lapse in faithfulness where the model defaults to parametric priors. To operationalize this diagnosis, we introduce Dual Reasoning Chain Editing, a mechanism that constructs controlled proxy chains to isolate reasoning structure from evidence faithfulness. We apply this method on **ReFaBench**, a novel benchmark constructed in this work featuring factual, counterfactual, and knowledge-conflicting scenarios. Furthermore, we propose **ReFa-DPO**, a decoupled preference optimization strategy that leverages these proxies to target specific failure patterns. Experimental results demonstrate that **ReFa-DPO** enhances robustness, particularly in mitigating parametric interference, by simultaneously enhancing both contextual faithfulness and reasoning capabilities.</abstract>
<identifier type="citekey">liu-etal-2026-beyond-correctness</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.135/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2628</start>
<end>2648</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Correctness: A Framework for Analyzing Reasoning and Faithfulness of Multi-hop Question Answering
%A Liu, Jiyuan
%A Xie, Yi
%A Rao, Yanghui
%A Wang, Fu Lee
%A Yu, Jianxing
%A Qing, Li
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F liu-etal-2026-beyond-correctness
%X Diagnosing the root causes of failures in Retrieval-Augmented Generation (RAG) is challenging, as current evaluations often conflate logical reasoning errors with the failure to adhere to retrieved context. To address this, we propose **ReFa**, a framework inspired by Structural Causal Models to explicitly disentangle *Reasoning* from *Faithfulness*. Through this lens, we characterize two distinct failure modes: the **‘Fool’**, representing a deficiency in logical reasoning, and the **‘Lazy’**, representing a lapse in faithfulness where the model defaults to parametric priors. To operationalize this diagnosis, we introduce Dual Reasoning Chain Editing, a mechanism that constructs controlled proxy chains to isolate reasoning structure from evidence faithfulness. We apply this method on **ReFaBench**, a novel benchmark constructed in this work featuring factual, counterfactual, and knowledge-conflicting scenarios. Furthermore, we propose **ReFa-DPO**, a decoupled preference optimization strategy that leverages these proxies to target specific failure patterns. Experimental results demonstrate that **ReFa-DPO** enhances robustness, particularly in mitigating parametric interference, by simultaneously enhancing both contextual faithfulness and reasoning capabilities.
%U https://aclanthology.org/2026.findings-aacl.135/
%P 2628-2648
Markdown (Informal)
[Beyond Correctness: A Framework for Analyzing Reasoning and Faithfulness of Multi-hop Question Answering](https://aclanthology.org/2026.findings-aacl.135/) (Liu et al., Findings 2026)
ACL