<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2025-probabilistic">
    <titleInfo>
        <title>A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bairu</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jacob</namePart>
        <namePart type="family">Andreas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shiyu</namePart>
        <namePart type="family">Chang</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>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</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">979-8-89176-189-6</identifier>
    </relatedItem>
    <abstract>We describe Belief Tree Propagation (BTProp), a probabilistic framework for LLM hallucination detection. To judge the truth of a statement, BTProp generates a belief tree by recursively expanding the initial statement into a set of logically related claims, then reasoning globally about the relationships between these claims. BTProp works by constructing a probabilistic model of the LM itself: it reasons jointly about logical relationships between claims and relationships between claim probabilities and LM factuality judgments via probabilistic inference in a “hidden Markov tree”. This method improves over state-of-the-art baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.</abstract>
    <identifier type="citekey">hou-etal-2025-probabilistic</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-long.158</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-long.158/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>3076</start>
            <end>3099</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation
%A Hou, Bairu
%A Zhang, Yang
%A Andreas, Jacob
%A Chang, Shiyu
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F hou-etal-2025-probabilistic
%X We describe Belief Tree Propagation (BTProp), a probabilistic framework for LLM hallucination detection. To judge the truth of a statement, BTProp generates a belief tree by recursively expanding the initial statement into a set of logically related claims, then reasoning globally about the relationships between these claims. BTProp works by constructing a probabilistic model of the LM itself: it reasons jointly about logical relationships between claims and relationships between claim probabilities and LM factuality judgments via probabilistic inference in a “hidden Markov tree”. This method improves over state-of-the-art baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.
%R 10.18653/v1/2025.naacl-long.158
%U https://aclanthology.org/2025.naacl-long.158/
%U https://doi.org/10.18653/v1/2025.naacl-long.158
%P 3076-3099

Markdown (Informal)

[A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://aclanthology.org/2025.naacl-long.158/) (Hou et al., NAACL 2025)

• A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation (Hou et al., NAACL 2025)

ACL

• Bairu Hou, Yang Zhang, Jacob Andreas, and Shiyu Chang. 2025. A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3076–3099, Albuquerque, New Mexico. Association for Computational Linguistics.