@inproceedings{zhang-etal-2024-getting,
title = "Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners",
author = "Zhang, Shimao and
Gao, Changjiang and
Zhu, Wenhao and
Chen, Jiajun and
Huang, Xin and
Han, Xue and
Feng, Junlan and
Deng, Chao and
Huang, Shujian",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.457",
pages = "8037--8051",
abstract = "Recently, Large Language Models (LLMs) have shown impressive language capabilities, while most of them have very unbalanced performance across different languages. Multilingual alignment based on the translation parallel data is an effective method to enhance LLMs{'} multilingual capabilities. In this work, we first discover and comprehensively investigate the spontaneous multilingual alignment of LLMs. Firstly, we find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages, even including those unseen during instruction-tuning. Additionally, we utilize different settings and mechanistic interpretability methods to analyze the LLM{'}s performance in the multilingual scenario comprehensively. Our work suggests that LLMs have enormous potential for improving multilingual alignment efficiently with great language generalization and task generalization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-getting">
<titleInfo>
<title>Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shimao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changjiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junlan</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Huang</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 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</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>Recently, Large Language Models (LLMs) have shown impressive language capabilities, while most of them have very unbalanced performance across different languages. Multilingual alignment based on the translation parallel data is an effective method to enhance LLMs’ multilingual capabilities. In this work, we first discover and comprehensively investigate the spontaneous multilingual alignment of LLMs. Firstly, we find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages, even including those unseen during instruction-tuning. Additionally, we utilize different settings and mechanistic interpretability methods to analyze the LLM’s performance in the multilingual scenario comprehensively. Our work suggests that LLMs have enormous potential for improving multilingual alignment efficiently with great language generalization and task generalization.</abstract>
<identifier type="citekey">zhang-etal-2024-getting</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.457</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8037</start>
<end>8051</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners
%A Zhang, Shimao
%A Gao, Changjiang
%A Zhu, Wenhao
%A Chen, Jiajun
%A Huang, Xin
%A Han, Xue
%A Feng, Junlan
%A Deng, Chao
%A Huang, Shujian
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhang-etal-2024-getting
%X Recently, Large Language Models (LLMs) have shown impressive language capabilities, while most of them have very unbalanced performance across different languages. Multilingual alignment based on the translation parallel data is an effective method to enhance LLMs’ multilingual capabilities. In this work, we first discover and comprehensively investigate the spontaneous multilingual alignment of LLMs. Firstly, we find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages, even including those unseen during instruction-tuning. Additionally, we utilize different settings and mechanistic interpretability methods to analyze the LLM’s performance in the multilingual scenario comprehensively. Our work suggests that LLMs have enormous potential for improving multilingual alignment efficiently with great language generalization and task generalization.
%U https://aclanthology.org/2024.emnlp-main.457
%P 8037-8051
Markdown (Informal)
[Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners](https://aclanthology.org/2024.emnlp-main.457) (Zhang et al., EMNLP 2024)
ACL
- Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, and Shujian Huang. 2024. Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8037–8051, Miami, Florida, USA. Association for Computational Linguistics.