@inproceedings{wang-etal-2023-zero,
title = "Zero-Shot Cross-Lingual Summarization via Large Language Models",
author = "Wang, Jiaan and
Liang, Yunlong and
Meng, Fandong and
Zou, Beiqi and
Li, Zhixu and
Qu, Jianfeng and
Zhou, Jie",
editor = "Dong, Yue and
Xiao, Wen and
Wang, Lu and
Liu, Fei and
Carenini, Giuseppe",
booktitle = "Proceedings of the 4th New Frontiers in Summarization Workshop",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.newsum-1.2",
doi = "10.18653/v1/2023.newsum-1.2",
pages = "12--23",
abstract = "Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language. Recently, the emergence of Large Language Models (LLMs), such as GPT-3.5, ChatGPT and GPT-4, has attracted wide attention from the computational linguistics community. However, it is not yet known the performance of LLMs on CLS. In this report, we empirically use various prompts to guide LLMs to perform zero-shot CLS from different paradigms (i.e., end-to-end and pipeline), and provide a preliminary evaluation on the generated summaries. We find that ChatGPT and GPT-4 originally prefer to produce lengthy summaries with detailed information. These two LLMs can further balance informativeness and conciseness with the help of an interactive prompt, significantly improving their CLS performance. Experimental results on three widely-used CLS datasets show that GPT-4 achieves state-of-the-art zero-shot CLS performance, and performs competitively compared with the fine-tuned mBART-50. Moreover, we also find some multi-lingual and bilingual LLMs (i.e., BLOOMZ, ChatGLM-6B, Vicuna-13B and ChatYuan) have limited zero-shot CLS ability. Due to the composite nature of CLS, which requires models to perform summarization and translation simultaneously, accomplishing this task in a zero-shot manner is even a challenge for LLMs. Therefore, we sincerely hope and recommend future LLM research could use CLS as a testbed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-zero">
<titleInfo>
<title>Zero-Shot Cross-Lingual Summarization via Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunlong</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beiqi</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th New Frontiers in Summarization Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language. Recently, the emergence of Large Language Models (LLMs), such as GPT-3.5, ChatGPT and GPT-4, has attracted wide attention from the computational linguistics community. However, it is not yet known the performance of LLMs on CLS. In this report, we empirically use various prompts to guide LLMs to perform zero-shot CLS from different paradigms (i.e., end-to-end and pipeline), and provide a preliminary evaluation on the generated summaries. We find that ChatGPT and GPT-4 originally prefer to produce lengthy summaries with detailed information. These two LLMs can further balance informativeness and conciseness with the help of an interactive prompt, significantly improving their CLS performance. Experimental results on three widely-used CLS datasets show that GPT-4 achieves state-of-the-art zero-shot CLS performance, and performs competitively compared with the fine-tuned mBART-50. Moreover, we also find some multi-lingual and bilingual LLMs (i.e., BLOOMZ, ChatGLM-6B, Vicuna-13B and ChatYuan) have limited zero-shot CLS ability. Due to the composite nature of CLS, which requires models to perform summarization and translation simultaneously, accomplishing this task in a zero-shot manner is even a challenge for LLMs. Therefore, we sincerely hope and recommend future LLM research could use CLS as a testbed.</abstract>
<identifier type="citekey">wang-etal-2023-zero</identifier>
<identifier type="doi">10.18653/v1/2023.newsum-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.newsum-1.2</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Cross-Lingual Summarization via Large Language Models
%A Wang, Jiaan
%A Liang, Yunlong
%A Meng, Fandong
%A Zou, Beiqi
%A Li, Zhixu
%A Qu, Jianfeng
%A Zhou, Jie
%Y Dong, Yue
%Y Xiao, Wen
%Y Wang, Lu
%Y Liu, Fei
%Y Carenini, Giuseppe
%S Proceedings of the 4th New Frontiers in Summarization Workshop
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wang-etal-2023-zero
%X Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language. Recently, the emergence of Large Language Models (LLMs), such as GPT-3.5, ChatGPT and GPT-4, has attracted wide attention from the computational linguistics community. However, it is not yet known the performance of LLMs on CLS. In this report, we empirically use various prompts to guide LLMs to perform zero-shot CLS from different paradigms (i.e., end-to-end and pipeline), and provide a preliminary evaluation on the generated summaries. We find that ChatGPT and GPT-4 originally prefer to produce lengthy summaries with detailed information. These two LLMs can further balance informativeness and conciseness with the help of an interactive prompt, significantly improving their CLS performance. Experimental results on three widely-used CLS datasets show that GPT-4 achieves state-of-the-art zero-shot CLS performance, and performs competitively compared with the fine-tuned mBART-50. Moreover, we also find some multi-lingual and bilingual LLMs (i.e., BLOOMZ, ChatGLM-6B, Vicuna-13B and ChatYuan) have limited zero-shot CLS ability. Due to the composite nature of CLS, which requires models to perform summarization and translation simultaneously, accomplishing this task in a zero-shot manner is even a challenge for LLMs. Therefore, we sincerely hope and recommend future LLM research could use CLS as a testbed.
%R 10.18653/v1/2023.newsum-1.2
%U https://aclanthology.org/2023.newsum-1.2
%U https://doi.org/10.18653/v1/2023.newsum-1.2
%P 12-23
Markdown (Informal)
[Zero-Shot Cross-Lingual Summarization via Large Language Models](https://aclanthology.org/2023.newsum-1.2) (Wang et al., NewSum 2023)
ACL