SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning

Page view(s)
4
Checked on Nov 10, 2024
SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
Title:
SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
Journal Title:
2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Keywords:
Publication Date:
01 June 2024
Citation:
Bin Wang, Zhengyuan Liu, Xin Huang, Fangkai Jiao, Yang Ding, AiTi Aw, and Nancy Chen. 2024. SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 370–390, Mexico City, Mexico. Association for Computational Linguistics.
Abstract:
We present SeaEval, a benchmark for multilingual foundation models. In addition to characterizing how these models understand and reason with natural language, we also investigate how well they comprehend cultural practices, nuances, and values. Alongside standard accuracy metrics, we investigate the brittleness of foundation models in the dimensions of semantics and multilinguality. Our analyses span both open-sourced and closed models, leading to empirical results across classic NLP tasks, reasoning, and cultural comprehension. Key findings indicate (1) Many models exhibit varied behavior when given paraphrased instructions. (2) Many models still suffer from exposure bias (e.g., positional bias, majority label bias). (3) For questions rooted in factual, scientific, and commonsense knowledge, consistent responses are expected across multilingual queries that are semantically equivalent. Yet, most models surprisingly demonstrate inconsistent performance on these queries. (4) Multilingually-trained models have not attained “balanced multilingual” capabilities. Our endeavors underscore the need for more generalizable semantic representations and enhanced multilingual contextualization. SeaEval can serve as a launchpad for more thorough investigations and evaluations for multilingual and multicultural scenarios.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the National Research Foundation - AISG
Grant Reference no. : AISG2-GC-2022-005
Description:
ISBN:

Files uploaded:

File Size Format Action
seaeval.pdf 2.75 MB PDF Open