@inproceedings{shankar-etal-2024-context,
title = "In-context Mixing ({ICM}): Code-mixed Prompts for Multilingual {LLM}s",
author = "Shankar, Bhavani and
Jyothi, Preethi and
Bhattacharyya, Pushpak",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.228",
pages = "4162--4176",
abstract = "We introduce a simple and effective prompting technique called in-context mixing (ICM) for effective in-context learning (ICL) with multilingual large language models (MLLMs). With ICM, we modify the few-shot examples within ICL prompts to be intra-sententially code-mixed by randomly swapping content words in the target languages with their English translations. We observe that ICM prompts yield superior performance in NLP tasks such as disfluency correction, grammar error correction and text simplification that demand a close correspondence between the input and output sequences. Significant improvements are observed mainly for low-resource languages that are under-represented during the pretraining and finetuning of MLLMs. We present an extensive set of experiments to analyze when ICM is effective and what design choices contribute towards its effectiveness. ICM works consistently and significantly better than other prompting techniques across models of varying capacity such as mT0-XXL, BloomZ and GPT-4.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shankar-etal-2024-context">
<titleInfo>
<title>In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavani</namePart>
<namePart type="family">Shankar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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>We introduce a simple and effective prompting technique called in-context mixing (ICM) for effective in-context learning (ICL) with multilingual large language models (MLLMs). With ICM, we modify the few-shot examples within ICL prompts to be intra-sententially code-mixed by randomly swapping content words in the target languages with their English translations. We observe that ICM prompts yield superior performance in NLP tasks such as disfluency correction, grammar error correction and text simplification that demand a close correspondence between the input and output sequences. Significant improvements are observed mainly for low-resource languages that are under-represented during the pretraining and finetuning of MLLMs. We present an extensive set of experiments to analyze when ICM is effective and what design choices contribute towards its effectiveness. ICM works consistently and significantly better than other prompting techniques across models of varying capacity such as mT0-XXL, BloomZ and GPT-4.</abstract>
<identifier type="citekey">shankar-etal-2024-context</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.228</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4162</start>
<end>4176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs
%A Shankar, Bhavani
%A Jyothi, Preethi
%A Bhattacharyya, Pushpak
%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 shankar-etal-2024-context
%X We introduce a simple and effective prompting technique called in-context mixing (ICM) for effective in-context learning (ICL) with multilingual large language models (MLLMs). With ICM, we modify the few-shot examples within ICL prompts to be intra-sententially code-mixed by randomly swapping content words in the target languages with their English translations. We observe that ICM prompts yield superior performance in NLP tasks such as disfluency correction, grammar error correction and text simplification that demand a close correspondence between the input and output sequences. Significant improvements are observed mainly for low-resource languages that are under-represented during the pretraining and finetuning of MLLMs. We present an extensive set of experiments to analyze when ICM is effective and what design choices contribute towards its effectiveness. ICM works consistently and significantly better than other prompting techniques across models of varying capacity such as mT0-XXL, BloomZ and GPT-4.
%U https://aclanthology.org/2024.acl-long.228
%P 4162-4176
Markdown (Informal)
[In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs](https://aclanthology.org/2024.acl-long.228) (Shankar et al., ACL 2024)
ACL
- Bhavani Shankar, Preethi Jyothi, and Pushpak Bhattacharyya. 2024. In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4162–4176, Bangkok, Thailand. Association for Computational Linguistics.