<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-generalizing">
    <titleInfo>
        <title>Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haonan</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhicheng</namePart>
        <namePart type="family">Dou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kelong</namePart>
        <namePart type="family">Mao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiongnan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziliang</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem – that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug). We first generate multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware prompting process to mitigate the generation of false positives, false negatives, and hallucinations. Moreover, we develop a difficulty-adaptive sample filter that selects challenging samples for complex conversations, thereby giving the model a larger learning space. A contrastive learning objective is then employed to train a better conversational context encoder. Extensive experiments conducted on four public datasets, under both normal and zero-shot settings, demonstrate the effectiveness, generalizability, and applicability of ConvAug. The code is released at https://github.com/haon-chen/ConvAug.</abstract>
    <identifier type="citekey">chen-etal-2024-generalizing</identifier>
    <identifier type="doi">10.18653/v1/2024.acl-long.149</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-long.149</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>2700</start>
            <end>2718</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
%A Chen, Haonan
%A Dou, Zhicheng
%A Mao, Kelong
%A Liu, Jiongnan
%A Zhao, Ziliang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chen-etal-2024-generalizing
%X Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem – that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug). We first generate multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware prompting process to mitigate the generation of false positives, false negatives, and hallucinations. Moreover, we develop a difficulty-adaptive sample filter that selects challenging samples for complex conversations, thereby giving the model a larger learning space. A contrastive learning objective is then employed to train a better conversational context encoder. Extensive experiments conducted on four public datasets, under both normal and zero-shot settings, demonstrate the effectiveness, generalizability, and applicability of ConvAug. The code is released at https://github.com/haon-chen/ConvAug.
%R 10.18653/v1/2024.acl-long.149
%U https://aclanthology.org/2024.acl-long.149
%U https://doi.org/10.18653/v1/2024.acl-long.149
%P 2700-2718

Markdown (Informal)

[Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation](https://aclanthology.org/2024.acl-long.149) (Chen et al., ACL 2024)

• Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation (Chen et al., ACL 2024)

ACL

• Haonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu, and Ziliang Zhao. 2024. Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2700–2718, Bangkok, Thailand. Association for Computational Linguistics.