@inproceedings{shi-etal-2026-iterative,
title = "Iterative Natural Logic Verification for Multi-hop Question Answering",
author = "Shi, Jihao and
Yang, Liang and
Lin, Hongfei",
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.2039/",
doi = "10.18653/2026.findings-emnlp.2039",
pages = "43407--43419",
ISBN = "979-8-89176-462-0",
abstract = "Multi-hop question answering requires composing multiple pieces of evidence to derive the correct answer, making it particularly vulnerable to hallucinated intermediate reasoning steps. A common failure mode arises when neural generators produce intermediate sentences that are fluent but logically inconsistent with the underlying facts, which can subsequently mislead downstream reasoning. In this paper, we propose ITERLOGIC, an iterative natural logic verification framework for multi-hop question answering, which explicitly integrates symbolic verification into the generation process. Specifically, a neural generator composes candidate intermediate sentences from retrieved facts, while a natural logic verifier evaluates their logical consistency with the source evidence. Low-scoring candidates are iteratively rejected and regenerated, allowing the system to progressively eliminate hallucinated compositions. This lightweight interaction upgrades natural logic from a passive scoring component to an active verification signal that guides intermediate sentence generation. Experiments on QASC, WorldTree, and WikiHop demonstrate that ITERLOGIC improves answer accuracy, highlighting the effectiveness of iterative verification for reliable multi-hop reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-iterative">
<titleInfo>
<title>Iterative Natural Logic Verification for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihao</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</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 question answering requires composing multiple pieces of evidence to derive the correct answer, making it particularly vulnerable to hallucinated intermediate reasoning steps. A common failure mode arises when neural generators produce intermediate sentences that are fluent but logically inconsistent with the underlying facts, which can subsequently mislead downstream reasoning. In this paper, we propose ITERLOGIC, an iterative natural logic verification framework for multi-hop question answering, which explicitly integrates symbolic verification into the generation process. Specifically, a neural generator composes candidate intermediate sentences from retrieved facts, while a natural logic verifier evaluates their logical consistency with the source evidence. Low-scoring candidates are iteratively rejected and regenerated, allowing the system to progressively eliminate hallucinated compositions. This lightweight interaction upgrades natural logic from a passive scoring component to an active verification signal that guides intermediate sentence generation. Experiments on QASC, WorldTree, and WikiHop demonstrate that ITERLOGIC improves answer accuracy, highlighting the effectiveness of iterative verification for reliable multi-hop reasoning.</abstract>
<identifier type="citekey">shi-etal-2026-iterative</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2039</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2039/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43407</start>
<end>43419</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Iterative Natural Logic Verification for Multi-hop Question Answering
%A Shi, Jihao
%A Yang, Liang
%A Lin, Hongfei
%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 shi-etal-2026-iterative
%X Multi-hop question answering requires composing multiple pieces of evidence to derive the correct answer, making it particularly vulnerable to hallucinated intermediate reasoning steps. A common failure mode arises when neural generators produce intermediate sentences that are fluent but logically inconsistent with the underlying facts, which can subsequently mislead downstream reasoning. In this paper, we propose ITERLOGIC, an iterative natural logic verification framework for multi-hop question answering, which explicitly integrates symbolic verification into the generation process. Specifically, a neural generator composes candidate intermediate sentences from retrieved facts, while a natural logic verifier evaluates their logical consistency with the source evidence. Low-scoring candidates are iteratively rejected and regenerated, allowing the system to progressively eliminate hallucinated compositions. This lightweight interaction upgrades natural logic from a passive scoring component to an active verification signal that guides intermediate sentence generation. Experiments on QASC, WorldTree, and WikiHop demonstrate that ITERLOGIC improves answer accuracy, highlighting the effectiveness of iterative verification for reliable multi-hop reasoning.
%R 10.18653/2026.findings-emnlp.2039
%U https://aclanthology.org/2026.findings-emnlp.2039/
%U https://doi.org/10.18653/2026.findings-emnlp.2039
%P 43407-43419
Markdown (Informal)
[Iterative Natural Logic Verification for Multi-hop Question Answering](https://aclanthology.org/2026.findings-emnlp.2039/) (Shi et al., Findings 2026)
ACL