@inproceedings{hashimoto-etal-2024-mlt,
title = "{MLT}-{DR}: Multi-Lingual/Task Demonstration RetrievalAn Attempt towards Generalized Retriever for In-Context Learning",
author = "Hashimoto, Kazuma and
Akula, Arjun Reddy and
Raman, Karthik and
Bendersky, Michael",
editor = {S{\"a}lev{\"a}, Jonne and
Owodunni, Abraham},
booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.mrl-1.27",
pages = "324--345",
abstract = "This paper presents Multi-Lingual/Task Demonstration Retrieval (MLT-DR) for in-context learning with Large Language Models (LLMs).Our goal is to investigate how dense demonstration retrieval models are generalized across languages and tasks.We first convert 81 tasks into a common format, covering various languages, task types, and domains.For 8 English-based tasks among them, we use machine translation to create synthetic multi/cross-lingual tasks, by translating the examples into non-English languages to explicitly cover more than 130 languages.We then use an instruction-tuned LLM to estimate utility of demonstrations for all the tasks to train the demonstration retrieval models.In our experiments, we show an interesting counterintuitive observation; to compute embeddings of demonstrations, using both the input and ground-truth output hurts the generalization ability of the retriever on unseen tasks whose output space is quite different from those in the seen task set.We also examine that our retriever robustly works even with LLMs that we did not touch during the development of the models.The retrieval models{'} checkpoints are publicly available at \url{URL-available-upon-publication}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hashimoto-etal-2024-mlt">
<titleInfo>
<title>MLT-DR: Multi-Lingual/Task Demonstration RetrievalAn Attempt towards Generalized Retriever for In-Context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuma</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Akula</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>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abraham</namePart>
<namePart type="family">Owodunni</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>This paper presents Multi-Lingual/Task Demonstration Retrieval (MLT-DR) for in-context learning with Large Language Models (LLMs).Our goal is to investigate how dense demonstration retrieval models are generalized across languages and tasks.We first convert 81 tasks into a common format, covering various languages, task types, and domains.For 8 English-based tasks among them, we use machine translation to create synthetic multi/cross-lingual tasks, by translating the examples into non-English languages to explicitly cover more than 130 languages.We then use an instruction-tuned LLM to estimate utility of demonstrations for all the tasks to train the demonstration retrieval models.In our experiments, we show an interesting counterintuitive observation; to compute embeddings of demonstrations, using both the input and ground-truth output hurts the generalization ability of the retriever on unseen tasks whose output space is quite different from those in the seen task set.We also examine that our retriever robustly works even with LLMs that we did not touch during the development of the models.The retrieval models’ checkpoints are publicly available at URL-available-upon-publication.</abstract>
<identifier type="citekey">hashimoto-etal-2024-mlt</identifier>
<location>
<url>https://aclanthology.org/2024.mrl-1.27</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>324</start>
<end>345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MLT-DR: Multi-Lingual/Task Demonstration RetrievalAn Attempt towards Generalized Retriever for In-Context Learning
%A Hashimoto, Kazuma
%A Akula, Arjun Reddy
%A Raman, Karthik
%A Bendersky, Michael
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F hashimoto-etal-2024-mlt
%X This paper presents Multi-Lingual/Task Demonstration Retrieval (MLT-DR) for in-context learning with Large Language Models (LLMs).Our goal is to investigate how dense demonstration retrieval models are generalized across languages and tasks.We first convert 81 tasks into a common format, covering various languages, task types, and domains.For 8 English-based tasks among them, we use machine translation to create synthetic multi/cross-lingual tasks, by translating the examples into non-English languages to explicitly cover more than 130 languages.We then use an instruction-tuned LLM to estimate utility of demonstrations for all the tasks to train the demonstration retrieval models.In our experiments, we show an interesting counterintuitive observation; to compute embeddings of demonstrations, using both the input and ground-truth output hurts the generalization ability of the retriever on unseen tasks whose output space is quite different from those in the seen task set.We also examine that our retriever robustly works even with LLMs that we did not touch during the development of the models.The retrieval models’ checkpoints are publicly available at URL-available-upon-publication.
%U https://aclanthology.org/2024.mrl-1.27
%P 324-345
Markdown (Informal)
[MLT-DR: Multi-Lingual/Task Demonstration RetrievalAn Attempt towards Generalized Retriever for In-Context Learning](https://aclanthology.org/2024.mrl-1.27) (Hashimoto et al., MRL 2024)
ACL