@inproceedings{hao-etal-2026-groundrag,
title = "{G}round{RAG}: Evidence-Verified Multi-Hop Reasoning on Lightweight Graphs",
author = "Hao, Jinjie and
Zhang, Guixuan and
Huang, Ying and
Liu, Jie and
Zhang, Shuwu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.336/",
pages = "7077--7089",
ISBN = "979-8-89176-462-0",
abstract = "Multi-hop Retrieval-Augmented Generation can fail even when relevant evidence has been retrieved. The remaining diffculty lies in how evidence is connected across reasoning steps:an intermediate answer may be unsupported, at-tached to the wrong anchor, or propagated into a later step without valid evidence. We study this failure as Reasoning Chain Hallucination(RCH), where a fuent multi-hop reasoning pro-cess contains one or more ungrounded inter-mediate steps. To address RCH, we formulate Retrieve{--}Verify{--}Generate (R-V-G) for multi-hop RAG: retrieved evidence should support an explicitly verifed reasoning structure before it is allowed to guide generation. GROUNDRAG is an evidence-verifed framework that imple-ments this requirement. GroundRAG frst ac-quires the evidence needed to instantiate inter-mediate reasoning variables, then represents the reasoning process as a typed dependency chain.Each step is checked against retrieved passages using explicit grounding criteria; unresolved steps are repaired with queries formed from ver-ifed intermediate answers, while insuffciently grounded chains are discarded before genera-tion. This design separates evidence acquisi-tion from the decision of whether a reasoning chain is safe to use. On HotpotQA, 2WikiMul-tiHopQA, and MuSiQue, GroundRAG reaches 73.8{\%}, 69.2{\%}, and 44.3{\%} LLM-judged accu-racy, respectively, outperforming the strongest baseline in our evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hao-etal-2026-groundrag">
<titleInfo>
<title>GroundRAG: Evidence-Verified Multi-Hop Reasoning on Lightweight Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinjie</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guixuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuwu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multi-hop Retrieval-Augmented Generation can fail even when relevant evidence has been retrieved. The remaining diffculty lies in how evidence is connected across reasoning steps:an intermediate answer may be unsupported, at-tached to the wrong anchor, or propagated into a later step without valid evidence. We study this failure as Reasoning Chain Hallucination(RCH), where a fuent multi-hop reasoning pro-cess contains one or more ungrounded inter-mediate steps. To address RCH, we formulate Retrieve–Verify–Generate (R-V-G) for multi-hop RAG: retrieved evidence should support an explicitly verifed reasoning structure before it is allowed to guide generation. GROUNDRAG is an evidence-verifed framework that imple-ments this requirement. GroundRAG frst ac-quires the evidence needed to instantiate inter-mediate reasoning variables, then represents the reasoning process as a typed dependency chain.Each step is checked against retrieved passages using explicit grounding criteria; unresolved steps are repaired with queries formed from ver-ifed intermediate answers, while insuffciently grounded chains are discarded before genera-tion. This design separates evidence acquisi-tion from the decision of whether a reasoning chain is safe to use. On HotpotQA, 2WikiMul-tiHopQA, and MuSiQue, GroundRAG reaches 73.8%, 69.2%, and 44.3% LLM-judged accu-racy, respectively, outperforming the strongest baseline in our evaluation.</abstract>
<identifier type="citekey">hao-etal-2026-groundrag</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.336/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7077</start>
<end>7089</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GroundRAG: Evidence-Verified Multi-Hop Reasoning on Lightweight Graphs
%A Hao, Jinjie
%A Zhang, Guixuan
%A Huang, Ying
%A Liu, Jie
%A Zhang, Shuwu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hao-etal-2026-groundrag
%X Multi-hop Retrieval-Augmented Generation can fail even when relevant evidence has been retrieved. The remaining diffculty lies in how evidence is connected across reasoning steps:an intermediate answer may be unsupported, at-tached to the wrong anchor, or propagated into a later step without valid evidence. We study this failure as Reasoning Chain Hallucination(RCH), where a fuent multi-hop reasoning pro-cess contains one or more ungrounded inter-mediate steps. To address RCH, we formulate Retrieve–Verify–Generate (R-V-G) for multi-hop RAG: retrieved evidence should support an explicitly verifed reasoning structure before it is allowed to guide generation. GROUNDRAG is an evidence-verifed framework that imple-ments this requirement. GroundRAG frst ac-quires the evidence needed to instantiate inter-mediate reasoning variables, then represents the reasoning process as a typed dependency chain.Each step is checked against retrieved passages using explicit grounding criteria; unresolved steps are repaired with queries formed from ver-ifed intermediate answers, while insuffciently grounded chains are discarded before genera-tion. This design separates evidence acquisi-tion from the decision of whether a reasoning chain is safe to use. On HotpotQA, 2WikiMul-tiHopQA, and MuSiQue, GroundRAG reaches 73.8%, 69.2%, and 44.3% LLM-judged accu-racy, respectively, outperforming the strongest baseline in our evaluation.
%U https://aclanthology.org/2026.findings-emnlp.336/
%P 7077-7089
Markdown (Informal)
[GroundRAG: Evidence-Verified Multi-Hop Reasoning on Lightweight Graphs](https://aclanthology.org/2026.findings-emnlp.336/) (Hao et al., Findings 2026)
ACL