Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
This work addresses the issue of linguistic equity in AI for multilingual NLP applications, but it appears incremental as it builds on existing editing methods without introducing a new paradigm.
The paper tackled the problem of linguistic imbalances in pretrained language models by investigating model editing techniques across multiple languages, finding significant discrepancies in cross-lingual consistency and demonstrating potential for overcoming linguistic barriers.
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.