Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yidan, Wan, Yu, Deng, Boyi, Yang, Baosong, Wei, Haoran, Huang, Fei, Yu, Bowen, Lin, Junyang, Zhou, Jingren
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.09116
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916736337444864
author Zhang, Yidan
Wan, Yu
Deng, Boyi
Yang, Baosong
Wei, Haoran
Huang, Fei
Yu, Bowen
Lin, Junyang
Huang, Fei
Zhou, Jingren
author_facet Zhang, Yidan
Wan, Yu
Deng, Boyi
Yang, Baosong
Wei, Haoran
Huang, Fei
Yu, Bowen
Lin, Junyang
Huang, Fei
Zhou, Jingren
contents Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning. Previous assessments often limited their scope to fundamental natural language processing (NLP) or isolated capability-specific tasks. To alleviate this drawback, we aim to present a comprehensive multilingual multitask benchmark. First, we introduce P-MMEval, a large-scale benchmark covering effective fundamental and capability-specialized datasets. Furthermore, P-MMEval delivers consistent language coverage across various datasets and provides parallel samples. Finally, we conduct extensive experiments on representative multilingual model series to compare performances across models and tasks, explore the relationship between multilingual performances and factors such as tasks, model sizes, languages, and prompts, and examine the effectiveness of knowledge transfer from English to other languages. The resulting insights are intended to offer valuable guidance for future research. The dataset is available at https://huggingface.co/datasets/Qwen/P-MMEval.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09116
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs
Zhang, Yidan
Wan, Yu
Deng, Boyi
Yang, Baosong
Wei, Haoran
Huang, Fei
Yu, Bowen
Lin, Junyang
Huang, Fei
Zhou, Jingren
Computation and Language
Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning. Previous assessments often limited their scope to fundamental natural language processing (NLP) or isolated capability-specific tasks. To alleviate this drawback, we aim to present a comprehensive multilingual multitask benchmark. First, we introduce P-MMEval, a large-scale benchmark covering effective fundamental and capability-specialized datasets. Furthermore, P-MMEval delivers consistent language coverage across various datasets and provides parallel samples. Finally, we conduct extensive experiments on representative multilingual model series to compare performances across models and tasks, explore the relationship between multilingual performances and factors such as tasks, model sizes, languages, and prompts, and examine the effectiveness of knowledge transfer from English to other languages. The resulting insights are intended to offer valuable guidance for future research. The dataset is available at https://huggingface.co/datasets/Qwen/P-MMEval.
title P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs
topic Computation and Language
url https://arxiv.org/abs/2411.09116