<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mazzaccara-etal-2024-learning">
    <titleInfo>
        <title>Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Davide</namePart>
        <namePart type="family">Mazzaccara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alberto</namePart>
        <namePart type="family">Testoni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raffaella</namePart>
        <namePart type="family">Bernardi</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>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Questions are essential tools for acquiring the necessary information to complete information-seeking tasks. However, large language models (LLMs), especially open-source models, often perform poorly in generating informative questions, as measured by expected information gain (EIG). In this paper, we propose a method to enhance the informativeness of LLM-generated questions in 20-question game dialogues. We sample multiple questions from the same model (LLaMA 2-Chat 7B) for each game and create pairs of low-EIG and high-EIG questions to apply a Direct Preference Optimization (DPO) algorithm. Our results show that this method produces more effective questions (in terms of EIG), even in domains different from those used to train the DPO model.</abstract>
    <identifier type="citekey">mazzaccara-etal-2024-learning</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.291</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>5064</start>
            <end>5074</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain
%A Mazzaccara, Davide
%A Testoni, Alberto
%A Bernardi, Raffaella
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mazzaccara-etal-2024-learning
%X Questions are essential tools for acquiring the necessary information to complete information-seeking tasks. However, large language models (LLMs), especially open-source models, often perform poorly in generating informative questions, as measured by expected information gain (EIG). In this paper, we propose a method to enhance the informativeness of LLM-generated questions in 20-question game dialogues. We sample multiple questions from the same model (LLaMA 2-Chat 7B) for each game and create pairs of low-EIG and high-EIG questions to apply a Direct Preference Optimization (DPO) algorithm. Our results show that this method produces more effective questions (in terms of EIG), even in domains different from those used to train the DPO model.
%U https://aclanthology.org/2024.findings-emnlp.291
%P 5064-5074

Markdown (Informal)

[Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain](https://aclanthology.org/2024.findings-emnlp.291) (Mazzaccara et al., Findings 2024)

• Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain (Mazzaccara et al., Findings 2024)

ACL

• Davide Mazzaccara, Alberto Testoni, and Raffaella Bernardi. 2024. Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5064–5074, Miami, Florida, USA. Association for Computational Linguistics.