@inproceedings{ganesh-etal-2026-rethinking,
title = "Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity",
author = "Ganesh, Prakhar and
Shokri, Reza and
Farnadi, Golnoosh",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.327/",
pages = "6959--6978",
ISBN = "979-8-89176-380-7",
abstract = "Large language models (LLMs) are known to ``hallucinate'' by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses only on correctness and often overlooks consistency, necessary to distinguish and address these harms. To bridge this gap, we introduce prompt multiplicity, a framework for quantifying consistency in LLM evaluations. Our analysis reveals significant multiplicity (over 50{\%} inconsistency in benchmarks like Med-HALT), suggesting that hallucination-related harms have been severely misunderstood. Furthermore, we study the role of consistency in hallucination detection and mitigation. We find that: (a) detection techniques detect consistency, not correctness, and (b) mitigation techniques like RAG, while beneficial, can introduce additional inconsistencies. By integrating prompt multiplicity into hallucination evaluation, we provide an improved framework of potential harms and uncover critical limitations in current detection and mitigation strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ganesh-etal-2026-rethinking">
<titleInfo>
<title>Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prakhar</namePart>
<namePart type="family">Ganesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Shokri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Golnoosh</namePart>
<namePart type="family">Farnadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are known to “hallucinate” by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses only on correctness and often overlooks consistency, necessary to distinguish and address these harms. To bridge this gap, we introduce prompt multiplicity, a framework for quantifying consistency in LLM evaluations. Our analysis reveals significant multiplicity (over 50% inconsistency in benchmarks like Med-HALT), suggesting that hallucination-related harms have been severely misunderstood. Furthermore, we study the role of consistency in hallucination detection and mitigation. We find that: (a) detection techniques detect consistency, not correctness, and (b) mitigation techniques like RAG, while beneficial, can introduce additional inconsistencies. By integrating prompt multiplicity into hallucination evaluation, we provide an improved framework of potential harms and uncover critical limitations in current detection and mitigation strategies.</abstract>
<identifier type="citekey">ganesh-etal-2026-rethinking</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.327/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>6959</start>
<end>6978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
%A Ganesh, Prakhar
%A Shokri, Reza
%A Farnadi, Golnoosh
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F ganesh-etal-2026-rethinking
%X Large language models (LLMs) are known to “hallucinate” by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses only on correctness and often overlooks consistency, necessary to distinguish and address these harms. To bridge this gap, we introduce prompt multiplicity, a framework for quantifying consistency in LLM evaluations. Our analysis reveals significant multiplicity (over 50% inconsistency in benchmarks like Med-HALT), suggesting that hallucination-related harms have been severely misunderstood. Furthermore, we study the role of consistency in hallucination detection and mitigation. We find that: (a) detection techniques detect consistency, not correctness, and (b) mitigation techniques like RAG, while beneficial, can introduce additional inconsistencies. By integrating prompt multiplicity into hallucination evaluation, we provide an improved framework of potential harms and uncover critical limitations in current detection and mitigation strategies.
%U https://aclanthology.org/2026.eacl-long.327/
%P 6959-6978
Markdown (Informal)
[Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity](https://aclanthology.org/2026.eacl-long.327/) (Ganesh et al., EACL 2026)
ACL