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

TL;DR

This paper evaluates how different model editing techniques affect multilingual language models' cross-linguistic performance, highlighting challenges and potential solutions for linguistic equity in NLP.

Contribution

It introduces new strategies like ELFI and ELFO to test and improve multilingual models' cross-lingual consistency and fairness.

Findings

Significant discrepancies in cross-lingual performance of models.

Strategies like ELFI and ELFO reveal model robustness and limitations.

Potential for models to better address linguistic diversity.

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.