@inproceedings{chaudhary-etal-2024-relative,
title = "It{'}s All Relative! {--} A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction",
author = "Chaudhary, Aditi and
Raman, Karthik and
Bendersky, Michael",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.107",
doi = "10.18653/v1/2024.findings-naacl.107",
pages = "1645--1664",
abstract = "Large language models (LLMs) have shown promising ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for tasks with no training data. Typically, such synthetic query generation (QGen) approaches condition on an input context (e.g. a text document) and generate a query relevant to that context, or condition the QGen additionally on the relevance label (e.g. relevant vs irrelevant) to generate queries across relevance buckets. However, we find that such QGen approaches are sub-optimal as they require the model to reason about the desired label and the input from a handful of examples. In this work, we propose to reduce this burden of LLMs by generating queries simultaneously for different labels. We hypothesize that instead of asking the model to generate, say, an irrelevant query given an input context, asking the model to generate an irrelevant query relative to a relevant query is a much simpler task. Extensive experimentation across nine IR datasets shows that synthetic queries generated in such a fashion translates to better downstream performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhary-etal-2024-relative">
<titleInfo>
<title>It’s All Relative! – A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Raman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Bendersky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have shown promising ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for tasks with no training data. Typically, such synthetic query generation (QGen) approaches condition on an input context (e.g. a text document) and generate a query relevant to that context, or condition the QGen additionally on the relevance label (e.g. relevant vs irrelevant) to generate queries across relevance buckets. However, we find that such QGen approaches are sub-optimal as they require the model to reason about the desired label and the input from a handful of examples. In this work, we propose to reduce this burden of LLMs by generating queries simultaneously for different labels. We hypothesize that instead of asking the model to generate, say, an irrelevant query given an input context, asking the model to generate an irrelevant query relative to a relevant query is a much simpler task. Extensive experimentation across nine IR datasets shows that synthetic queries generated in such a fashion translates to better downstream performance.</abstract>
<identifier type="citekey">chaudhary-etal-2024-relative</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.107</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.107</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1645</start>
<end>1664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T It’s All Relative! – A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction
%A Chaudhary, Aditi
%A Raman, Karthik
%A Bendersky, Michael
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F chaudhary-etal-2024-relative
%X Large language models (LLMs) have shown promising ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for tasks with no training data. Typically, such synthetic query generation (QGen) approaches condition on an input context (e.g. a text document) and generate a query relevant to that context, or condition the QGen additionally on the relevance label (e.g. relevant vs irrelevant) to generate queries across relevance buckets. However, we find that such QGen approaches are sub-optimal as they require the model to reason about the desired label and the input from a handful of examples. In this work, we propose to reduce this burden of LLMs by generating queries simultaneously for different labels. We hypothesize that instead of asking the model to generate, say, an irrelevant query given an input context, asking the model to generate an irrelevant query relative to a relevant query is a much simpler task. Extensive experimentation across nine IR datasets shows that synthetic queries generated in such a fashion translates to better downstream performance.
%R 10.18653/v1/2024.findings-naacl.107
%U https://aclanthology.org/2024.findings-naacl.107
%U https://doi.org/10.18653/v1/2024.findings-naacl.107
%P 1645-1664
Markdown (Informal)
[It’s All Relative! – A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction](https://aclanthology.org/2024.findings-naacl.107) (Chaudhary et al., Findings 2024)
ACL