@inproceedings{dai-etal-2026-response,
title = "When Response Variation Does Not Indicate Uncertainty: Hallucination Detection for Multi-Answer Queries",
author = "Dai, Hongliang and
Li, Qiuyuan and
Li, Piji",
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.864/",
pages = "19989--20013",
ISBN = "979-8-89176-459-0",
abstract = "Hallucination detection in LLMs often relies on output consistency or model-internal signals. While output-based methods have the advantage of applicability to closed-source models, existing studies often overlook a key limitation: they struggle on tasks that admit multiple valid answers, where variation across generations may reflect legitimate alternative responses rather than hallucinations. In this paper, we propose a question-type-aware hallucination detection framework that distinguishes single-answer and multi-answer regimes. Given a predicted question-type signal, we derive type-conditioned diagnostic features from low- and high-temperature generations, and build two alternative hallucination detectors based on these features: a calibrated type-aware uncertainty estimator and a feature-verbalized few-shot LLM judge. Experiments on NQ-Open, WebQA, and AmbigQA across both open-source and closed-source LLMs demonstrate that our method consistently outperforms conventional semantic clustering approaches and representative baselines in hallucination detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-etal-2026-response">
<titleInfo>
<title>When Response Variation Does Not Indicate Uncertainty: Hallucination Detection for Multi-Answer Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongliang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piji</namePart>
<namePart type="family">Li</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>Hallucination detection in LLMs often relies on output consistency or model-internal signals. While output-based methods have the advantage of applicability to closed-source models, existing studies often overlook a key limitation: they struggle on tasks that admit multiple valid answers, where variation across generations may reflect legitimate alternative responses rather than hallucinations. In this paper, we propose a question-type-aware hallucination detection framework that distinguishes single-answer and multi-answer regimes. Given a predicted question-type signal, we derive type-conditioned diagnostic features from low- and high-temperature generations, and build two alternative hallucination detectors based on these features: a calibrated type-aware uncertainty estimator and a feature-verbalized few-shot LLM judge. Experiments on NQ-Open, WebQA, and AmbigQA across both open-source and closed-source LLMs demonstrate that our method consistently outperforms conventional semantic clustering approaches and representative baselines in hallucination detection.</abstract>
<identifier type="citekey">dai-etal-2026-response</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.864/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>19989</start>
<end>20013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Response Variation Does Not Indicate Uncertainty: Hallucination Detection for Multi-Answer Queries
%A Dai, Hongliang
%A Li, Qiuyuan
%A Li, Piji
%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 dai-etal-2026-response
%X Hallucination detection in LLMs often relies on output consistency or model-internal signals. While output-based methods have the advantage of applicability to closed-source models, existing studies often overlook a key limitation: they struggle on tasks that admit multiple valid answers, where variation across generations may reflect legitimate alternative responses rather than hallucinations. In this paper, we propose a question-type-aware hallucination detection framework that distinguishes single-answer and multi-answer regimes. Given a predicted question-type signal, we derive type-conditioned diagnostic features from low- and high-temperature generations, and build two alternative hallucination detectors based on these features: a calibrated type-aware uncertainty estimator and a feature-verbalized few-shot LLM judge. Experiments on NQ-Open, WebQA, and AmbigQA across both open-source and closed-source LLMs demonstrate that our method consistently outperforms conventional semantic clustering approaches and representative baselines in hallucination detection.
%U https://aclanthology.org/2026.emnlp-main.864/
%P 19989-20013
Markdown (Informal)
[When Response Variation Does Not Indicate Uncertainty: Hallucination Detection for Multi-Answer Queries](https://aclanthology.org/2026.emnlp-main.864/) (Dai et al., EMNLP 2026)
ACL