@inproceedings{chatterjee-etal-2026-hat,
title = "{HAT}: Hallucination Annotation for Translation",
author = "Chatterjee, Rajen and
Li, Xintong and
Charoenpornsawat, Paisarn and
Lee, Allen",
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.721/",
pages = "15865--15888",
ISBN = "979-8-89176-390-6",
abstract = "Hallucinations in machine translation (MT){---}outputs that may be fluent yet unfaithful to the source content{---}remain a critical obstacle. They hinder the reliable deployment of MT systems in real-world applications. Despite growing attention to this phenomenon, progress has been constrained by the lack of large-scale, high-quality benchmarks dedicated to hallucination detection. We introduce HAT (Hallucination Annotation for Translation), a novel dataset designed to advance research on this problem. HAT comprises 350,959 span-level annotated samples across 38 language pairs, with approximately $8,000–10,000$ samples per pair partitioned into training, development, and test sets. Annotations were produced by professional translators under rigorous quality control protocols to ensure reliability. We provide a detailed analysis of hallucination distributions and establish benchmark performance using a diverse set of baselines, including automatic MT evaluation metrics as well as large language models. By providing the first large-scale, systematically annotated resource for hallucination detection in MT, HAT enables the development of more faithful translation models and lays the groundwork for future research on building trustworthy machine translation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatterjee-etal-2026-hat">
<titleInfo>
<title>HAT: Hallucination Annotation for Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xintong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paisarn</namePart>
<namePart type="family">Charoenpornsawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allen</namePart>
<namePart type="family">Lee</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>Hallucinations in machine translation (MT)—outputs that may be fluent yet unfaithful to the source content—remain a critical obstacle. They hinder the reliable deployment of MT systems in real-world applications. Despite growing attention to this phenomenon, progress has been constrained by the lack of large-scale, high-quality benchmarks dedicated to hallucination detection. We introduce HAT (Hallucination Annotation for Translation), a novel dataset designed to advance research on this problem. HAT comprises 350,959 span-level annotated samples across 38 language pairs, with approximately 8,000–10,000 samples per pair partitioned into training, development, and test sets. Annotations were produced by professional translators under rigorous quality control protocols to ensure reliability. We provide a detailed analysis of hallucination distributions and establish benchmark performance using a diverse set of baselines, including automatic MT evaluation metrics as well as large language models. By providing the first large-scale, systematically annotated resource for hallucination detection in MT, HAT enables the development of more faithful translation models and lays the groundwork for future research on building trustworthy machine translation systems.</abstract>
<identifier type="citekey">chatterjee-etal-2026-hat</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.721/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>15865</start>
<end>15888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HAT: Hallucination Annotation for Translation
%A Chatterjee, Rajen
%A Li, Xintong
%A Charoenpornsawat, Paisarn
%A Lee, Allen
%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 chatterjee-etal-2026-hat
%X Hallucinations in machine translation (MT)—outputs that may be fluent yet unfaithful to the source content—remain a critical obstacle. They hinder the reliable deployment of MT systems in real-world applications. Despite growing attention to this phenomenon, progress has been constrained by the lack of large-scale, high-quality benchmarks dedicated to hallucination detection. We introduce HAT (Hallucination Annotation for Translation), a novel dataset designed to advance research on this problem. HAT comprises 350,959 span-level annotated samples across 38 language pairs, with approximately 8,000–10,000 samples per pair partitioned into training, development, and test sets. Annotations were produced by professional translators under rigorous quality control protocols to ensure reliability. We provide a detailed analysis of hallucination distributions and establish benchmark performance using a diverse set of baselines, including automatic MT evaluation metrics as well as large language models. By providing the first large-scale, systematically annotated resource for hallucination detection in MT, HAT enables the development of more faithful translation models and lays the groundwork for future research on building trustworthy machine translation systems.
%U https://aclanthology.org/2026.acl-long.721/
%P 15865-15888
Markdown (Informal)
[HAT: Hallucination Annotation for Translation](https://aclanthology.org/2026.acl-long.721/) (Chatterjee et al., ACL 2026)
ACL
- Rajen Chatterjee, Xintong Li, Paisarn Charoenpornsawat, and Allen Lee. 2026. HAT: Hallucination Annotation for Translation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15865–15888, San Diego, California, United States. Association for Computational Linguistics.