@inproceedings{mao-etal-2026-digital,
title = "The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness",
author = "Mao, Yueheng and
Yu, Min and
Li, Gengwang and
Jiang, Jianguo and
Li, Gang and
Zhang, Meng and
Xu, Zhen and
Huang, Weiqing and
Liu, Ming",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.993/",
pages = "21786--21800",
ISBN = "979-8-89176-390-6",
abstract = "Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations. Current detection paradigms suffer from a trade-off between the high accuracy of computationally expensive black-box methods and the inability of white-box methods to detect stubborn hallucinations. To bridge this gap, we propose GHOST (Geometric Hidden-state Observation for Semantic Truthfulness), an efficient white-box framework for hallucination detection in LLMs. We primarily target confused hallucinations marked by internal reasoning instability, while also capturing stubborn hallucinations characterized by premature layer-wise convergence as a complementary signal. By integrating internal geometric dynamics with output probability distributions, GHOST constructs a high-dimensional feature space for non-linear truthfulness classification. Extensive evaluations on FinanceBench, RAGTruth, HaluEval, and PopQA show that GHOST outperforms white-box baselines and achieves competitive black-box performance while reducing computational overhead by over 90{\%}, offering a robust solution for real-time detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-etal-2026-digital">
<titleInfo>
<title>The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yueheng</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gengwang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianguo</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiqing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations. Current detection paradigms suffer from a trade-off between the high accuracy of computationally expensive black-box methods and the inability of white-box methods to detect stubborn hallucinations. To bridge this gap, we propose GHOST (Geometric Hidden-state Observation for Semantic Truthfulness), an efficient white-box framework for hallucination detection in LLMs. We primarily target confused hallucinations marked by internal reasoning instability, while also capturing stubborn hallucinations characterized by premature layer-wise convergence as a complementary signal. By integrating internal geometric dynamics with output probability distributions, GHOST constructs a high-dimensional feature space for non-linear truthfulness classification. Extensive evaluations on FinanceBench, RAGTruth, HaluEval, and PopQA show that GHOST outperforms white-box baselines and achieves competitive black-box performance while reducing computational overhead by over 90%, offering a robust solution for real-time detection.</abstract>
<identifier type="citekey">mao-etal-2026-digital</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.993/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>21786</start>
<end>21800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness
%A Mao, Yueheng
%A Yu, Min
%A Li, Gengwang
%A Jiang, Jianguo
%A Li, Gang
%A Zhang, Meng
%A Xu, Zhen
%A Huang, Weiqing
%A Liu, Ming
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F mao-etal-2026-digital
%X Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations. Current detection paradigms suffer from a trade-off between the high accuracy of computationally expensive black-box methods and the inability of white-box methods to detect stubborn hallucinations. To bridge this gap, we propose GHOST (Geometric Hidden-state Observation for Semantic Truthfulness), an efficient white-box framework for hallucination detection in LLMs. We primarily target confused hallucinations marked by internal reasoning instability, while also capturing stubborn hallucinations characterized by premature layer-wise convergence as a complementary signal. By integrating internal geometric dynamics with output probability distributions, GHOST constructs a high-dimensional feature space for non-linear truthfulness classification. Extensive evaluations on FinanceBench, RAGTruth, HaluEval, and PopQA show that GHOST outperforms white-box baselines and achieves competitive black-box performance while reducing computational overhead by over 90%, offering a robust solution for real-time detection.
%U https://aclanthology.org/2026.acl-long.993/
%P 21786-21800
Markdown (Informal)
[The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness](https://aclanthology.org/2026.acl-long.993/) (Mao et al., ACL 2026)
ACL
- Yueheng Mao, Min Yu, Gengwang Li, Jianguo Jiang, Gang Li, Meng Zhang, Zhen Xu, Weiqing Huang, and Ming Liu. 2026. The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 21786–21800, San Diego, California, United States. Association for Computational Linguistics.