@inproceedings{ma-etal-2026-target,
title = "Target-Binding Hallucination: A Position-Controlled Diagnostic for Multimodal {LLM}s in Multi-Image Contexts",
author = "Ma, Qichao and
Liu, Yongtai and
Zhu, Xuan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.691/",
pages = "15887--15906",
ISBN = "979-8-89176-459-0",
abstract = "Multimodal LLMs are increasingly used with multi-image, interleaved image-text inputs, yet hallucination evaluation remains largely single-image. We study target-binding hallucination: a model answers as if an object appears in the queried target image when it appears only elsewhere. We introduce a position-controlled COCO haystack with POPE-style object-existence queries and split negatives into clean cases (object absent everywhere) and distractor-present cases (absent from the target but present elsewhere). On InternVL2-8B at N = 10, clean false positives remain near floor (1.15{\%}), whereas distractor-present cases reach 10.55{\%} and show a position-sensitive profile; the same regime-level separation appears across three additional architectures and in an object-balanced PASCAL VOC2012 check. Channel and paired-removal controls are consistent with a visual-channel-dominant source-misattribution interpretation, and a related MIHBench Existence re-audit finds that over 98{\%} of false positives concentrate in partial-present negatives. For object-existence diagnostics and other source-sensitive multi-image evaluations with auditable negative evidence, we recommend reporting clean and evidence-supported negatives separately whenever non-target images may contain supporting evidence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2026-target">
<titleInfo>
<title>Target-Binding Hallucination: A Position-Controlled Diagnostic for Multimodal LLMs in Multi-Image Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qichao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongtai</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhu</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Multimodal LLMs are increasingly used with multi-image, interleaved image-text inputs, yet hallucination evaluation remains largely single-image. We study target-binding hallucination: a model answers as if an object appears in the queried target image when it appears only elsewhere. We introduce a position-controlled COCO haystack with POPE-style object-existence queries and split negatives into clean cases (object absent everywhere) and distractor-present cases (absent from the target but present elsewhere). On InternVL2-8B at N = 10, clean false positives remain near floor (1.15%), whereas distractor-present cases reach 10.55% and show a position-sensitive profile; the same regime-level separation appears across three additional architectures and in an object-balanced PASCAL VOC2012 check. Channel and paired-removal controls are consistent with a visual-channel-dominant source-misattribution interpretation, and a related MIHBench Existence re-audit finds that over 98% of false positives concentrate in partial-present negatives. For object-existence diagnostics and other source-sensitive multi-image evaluations with auditable negative evidence, we recommend reporting clean and evidence-supported negatives separately whenever non-target images may contain supporting evidence.</abstract>
<identifier type="citekey">ma-etal-2026-target</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.691/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>15887</start>
<end>15906</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Target-Binding Hallucination: A Position-Controlled Diagnostic for Multimodal LLMs in Multi-Image Contexts
%A Ma, Qichao
%A Liu, Yongtai
%A Zhu, Xuan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F ma-etal-2026-target
%X Multimodal LLMs are increasingly used with multi-image, interleaved image-text inputs, yet hallucination evaluation remains largely single-image. We study target-binding hallucination: a model answers as if an object appears in the queried target image when it appears only elsewhere. We introduce a position-controlled COCO haystack with POPE-style object-existence queries and split negatives into clean cases (object absent everywhere) and distractor-present cases (absent from the target but present elsewhere). On InternVL2-8B at N = 10, clean false positives remain near floor (1.15%), whereas distractor-present cases reach 10.55% and show a position-sensitive profile; the same regime-level separation appears across three additional architectures and in an object-balanced PASCAL VOC2012 check. Channel and paired-removal controls are consistent with a visual-channel-dominant source-misattribution interpretation, and a related MIHBench Existence re-audit finds that over 98% of false positives concentrate in partial-present negatives. For object-existence diagnostics and other source-sensitive multi-image evaluations with auditable negative evidence, we recommend reporting clean and evidence-supported negatives separately whenever non-target images may contain supporting evidence.
%U https://aclanthology.org/2026.emnlp-main.691/
%P 15887-15906
Markdown (Informal)
[Target-Binding Hallucination: A Position-Controlled Diagnostic for Multimodal LLMs in Multi-Image Contexts](https://aclanthology.org/2026.emnlp-main.691/) (Ma et al., EMNLP 2026)
ACL