@article{zhang-etal-2025-sirens,
title = "🧜{S}iren{'}s Song in the {AI} Ocean: A Survey on Hallucination in Large Language Models",
author = "Zhang, Yue and
Li, Yafu and
Cui, Leyang and
Cai, Deng and
Liu, Lemao and
Fu, Tingchen and
Huang, Xinting and
Zhao, Enbo and
Zhang, Yu and
Chen, Yulong and
Wang, Longyue and
Luu, Anh Tuan and
Bi, Wei and
Shi, Freda and
Shi, Shuming",
journal = "Computational Linguistics",
volume = "51",
number = "4",
month = dec,
year = "2025",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2025.cl-4.9/",
doi = "10.1162/coli.a.16",
pages = "1373--1418",
abstract = "While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this article, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-sirens">
<titleInfo>
<title>🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yafu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deng</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingchen</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinting</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enbo</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this article, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.</abstract>
<identifier type="citekey">zhang-etal-2025-sirens</identifier>
<identifier type="doi">10.1162/coli.a.16</identifier>
<location>
<url>https://aclanthology.org/2025.cl-4.9/</url>
</location>
<part>
<date>2025-12</date>
<detail type="volume"><number>51</number></detail>
<detail type="issue"><number>4</number></detail>
<extent unit="page">
<start>1373</start>
<end>1418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T 🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models
%A Zhang, Yue
%A Li, Yafu
%A Cui, Leyang
%A Cai, Deng
%A Liu, Lemao
%A Fu, Tingchen
%A Huang, Xinting
%A Zhao, Enbo
%A Zhang, Yu
%A Chen, Yulong
%A Wang, Longyue
%A Luu, Anh Tuan
%A Bi, Wei
%A Shi, Freda
%A Shi, Shuming
%J Computational Linguistics
%D 2025
%8 December
%V 51
%N 4
%I MIT Press
%C Cambridge, MA
%F zhang-etal-2025-sirens
%X While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this article, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
%R 10.1162/coli.a.16
%U https://aclanthology.org/2025.cl-4.9/
%U https://doi.org/10.1162/coli.a.16
%P 1373-1418
Markdown (Informal)
[🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://aclanthology.org/2025.cl-4.9/) (Zhang et al., CL 2025)
ACL
- Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. 2025. 🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. Computational Linguistics, 51(4):1373–1418.