<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-hallucana">
    <titleInfo>
        <title>HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianyi</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Erenay</namePart>
        <namePart type="family">Dayanik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shubhi</namePart>
        <namePart type="family">Tyagi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Pierleoni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-195-7</identifier>
    </relatedItem>
    <abstract>In this paper, we present HALLUCANA, a canary lookahead to detect and correct factual hallucinations of Large Language Models (LLMs) in long-form generation. HALLUCANA detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs’ factuality self-assessment, and discuss its relation to the models’ context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute.</abstract>
    <identifier type="citekey">li-etal-2025-hallucana</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.12</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.12/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>213</start>
            <end>230</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead
%A Li, Tianyi
%A Dayanik, Erenay
%A Tyagi, Shubhi
%A Pierleoni, Andrea
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F li-etal-2025-hallucana
%X In this paper, we present HALLUCANA, a canary lookahead to detect and correct factual hallucinations of Large Language Models (LLMs) in long-form generation. HALLUCANA detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs’ factuality self-assessment, and discuss its relation to the models’ context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute.
%R 10.18653/v1/2025.findings-naacl.12
%U https://aclanthology.org/2025.findings-naacl.12/
%U https://doi.org/10.18653/v1/2025.findings-naacl.12
%P 213-230

Markdown (Informal)

[HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead](https://aclanthology.org/2025.findings-naacl.12/) (Li et al., Findings 2025)

• HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead (Li et al., Findings 2025)

ACL

• Tianyi Li, Erenay Dayanik, Shubhi Tyagi, and Andrea Pierleoni. 2025. HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 213–230, Albuquerque, New Mexico. Association for Computational Linguistics.