Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance

Published

June 17, 2024

Author(s)

Somnath Banerjee, Avik Halder, Rajarshi Mandal, Sayan Layek, Ian Soboroff, Rima Hazra, Animesh Mukherjee

Abstract

The integration of pretrained language models (PLMs) like BERT and GPT has revolutionized NLP, particularly for English, but it has also created linguistic imbalances. This paper strategically identifies the need for linguistic equity by examining several knowledge editing techniques in multilingual contexts. We evaluate the performance of models such as Mistral, TowerInstruct, OpenHathi, Tamil-Llama, and Kan-Llama across languages including English, German, French, Italian, Spanish, Hindi, Tamil, and Kannada. Our research identifies significant discrepancies in normal and merged models concerning cross-lingual consistency. We employ strategies like 'each language for itself' (ELFI) and 'each language for others' (ELFO) to stress-test these models. Our findings demonstrate the potential for LLMs to overcome linguistic barriers, laying the groundwork for future research in achieving linguistic inclusivity in AI technologies.

Citation

This is in the Association of Computational Linguistics rolling review process, so the conference isn't known at submission time.

Pub Type

Journals

Keywords

large language models, low resource languages

Citation

Banerjee, S. , Halder, A. , Mandal, R. , Layek, S. , Soboroff, I. , Hazra, R. and Mukherjee, A. (2024), Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance, This is in the Association of Computational Linguistics rolling review process, so the conference isn't known at submission time. (Accessed April 19, 2025)