<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zimmerman-etal-2024-two">
    <titleInfo>
        <title>Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ilana</namePart>
        <namePart type="family">Zimmerman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jadin</namePart>
        <namePart type="family">Tredup</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ethan</namePart>
        <namePart type="family">Selfridge</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="family">Bradley</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Franck</namePart>
            <namePart type="family">Dernoncourt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoţiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anastasia</namePart>
            <namePart type="family">Shimorina</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, US</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Detecting hallucinations, where Large Language Models (LLMs) are not factually consistent with a Knowledge Base (KB), is a challenge for Retrieval-Augmented Generation (RAG) systems. Current solutions rely on public datasets to develop prompts or fine-tune a Natural Language Inference (NLI) model. However, these approaches are not focused on developing an enterprise RAG system; they do not consider latency, train or evaluate on production data, nor do they handle non-verifiable statements such as small talk or questions. To address this, we leverage the customer service conversation data of four large brands to evaluate existing solutions and propose a set of small encoder models trained on a new dataset. We find the proposed models to outperform existing methods and highlight the value of combining a small amount of in-domain data with public datasets.</abstract>
    <identifier type="citekey">zimmerman-etal-2024-two</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-industry.2</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>8</start>
            <end>22</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild
%A Zimmerman, Ilana
%A Tredup, Jadin
%A Selfridge, Ethan
%A Bradley, Joseph
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F zimmerman-etal-2024-two
%X Detecting hallucinations, where Large Language Models (LLMs) are not factually consistent with a Knowledge Base (KB), is a challenge for Retrieval-Augmented Generation (RAG) systems. Current solutions rely on public datasets to develop prompts or fine-tune a Natural Language Inference (NLI) model. However, these approaches are not focused on developing an enterprise RAG system; they do not consider latency, train or evaluate on production data, nor do they handle non-verifiable statements such as small talk or questions. To address this, we leverage the customer service conversation data of four large brands to evaluate existing solutions and propose a set of small encoder models trained on a new dataset. We find the proposed models to outperform existing methods and highlight the value of combining a small amount of in-domain data with public datasets.
%U https://aclanthology.org/2024.emnlp-industry.2
%P 8-22

Markdown (Informal)

[Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild](https://aclanthology.org/2024.emnlp-industry.2) (Zimmerman et al., EMNLP 2024)

• Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild (Zimmerman et al., EMNLP 2024)

ACL

• Ilana Zimmerman, Jadin Tredup, Ethan Selfridge, and Joseph Bradley. 2024. Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 8–22, Miami, Florida, US. Association for Computational Linguistics.