@inproceedings{adeyemi-etal-2024-zero,
title = "Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages",
author = "Adeyemi, Mofetoluwa and
Oladipo, Akintunde and
Pradeep, Ronak and
Lin, Jimmy",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-short.59",
pages = "650--656",
abstract = "Large language models (LLMs) as listwise rerankers have shown impressive zero-shot capabilities in various passage ranking tasks. Despite their success, there is still a gap in existing literature on their effectiveness in reranking low-resource languages. To address this, we investigate how LLMs function as listwise rerankers in cross-lingual information retrieval (CLIR) systems with queries in English and passages in four African languages: Hausa, Somali, Swahili, and Yoruba. We analyze and compare the effectiveness of monolingual reranking using either query or document translations. We also evaluate the effectiveness of LLMs when leveraging their own generated translations. To grasp the general picture, we examine the effectiveness of multiple LLMs {---} the proprietary models RankGPT-4 and RankGPT-3.5, along with the open-source model RankZephyr. While the document translation setting, i.e., both queries and documents are in English, leads to the best reranking effectiveness, our results indicate that for specific LLMs, reranking in the African language setting achieves competitive effectiveness with the cross-lingual setting, and even performs better when using the LLM{'}s own translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adeyemi-etal-2024-zero">
<titleInfo>
<title>Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mofetoluwa</namePart>
<namePart type="family">Adeyemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akintunde</namePart>
<namePart type="family">Oladipo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronak</namePart>
<namePart type="family">Pradeep</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Lin</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 2: Short 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>Large language models (LLMs) as listwise rerankers have shown impressive zero-shot capabilities in various passage ranking tasks. Despite their success, there is still a gap in existing literature on their effectiveness in reranking low-resource languages. To address this, we investigate how LLMs function as listwise rerankers in cross-lingual information retrieval (CLIR) systems with queries in English and passages in four African languages: Hausa, Somali, Swahili, and Yoruba. We analyze and compare the effectiveness of monolingual reranking using either query or document translations. We also evaluate the effectiveness of LLMs when leveraging their own generated translations. To grasp the general picture, we examine the effectiveness of multiple LLMs — the proprietary models RankGPT-4 and RankGPT-3.5, along with the open-source model RankZephyr. While the document translation setting, i.e., both queries and documents are in English, leads to the best reranking effectiveness, our results indicate that for specific LLMs, reranking in the African language setting achieves competitive effectiveness with the cross-lingual setting, and even performs better when using the LLM’s own translations.</abstract>
<identifier type="citekey">adeyemi-etal-2024-zero</identifier>
<location>
<url>https://aclanthology.org/2024.acl-short.59</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>650</start>
<end>656</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages
%A Adeyemi, Mofetoluwa
%A Oladipo, Akintunde
%A Pradeep, Ronak
%A Lin, Jimmy
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F adeyemi-etal-2024-zero
%X Large language models (LLMs) as listwise rerankers have shown impressive zero-shot capabilities in various passage ranking tasks. Despite their success, there is still a gap in existing literature on their effectiveness in reranking low-resource languages. To address this, we investigate how LLMs function as listwise rerankers in cross-lingual information retrieval (CLIR) systems with queries in English and passages in four African languages: Hausa, Somali, Swahili, and Yoruba. We analyze and compare the effectiveness of monolingual reranking using either query or document translations. We also evaluate the effectiveness of LLMs when leveraging their own generated translations. To grasp the general picture, we examine the effectiveness of multiple LLMs — the proprietary models RankGPT-4 and RankGPT-3.5, along with the open-source model RankZephyr. While the document translation setting, i.e., both queries and documents are in English, leads to the best reranking effectiveness, our results indicate that for specific LLMs, reranking in the African language setting achieves competitive effectiveness with the cross-lingual setting, and even performs better when using the LLM’s own translations.
%U https://aclanthology.org/2024.acl-short.59
%P 650-656
Markdown (Informal)
[Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages](https://aclanthology.org/2024.acl-short.59) (Adeyemi et al., ACL 2024)
ACL