← Search

Félix Gaschi

2 accepted papers

2025

AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages

NAACL 2025short

Realignment techniques are often employed to enhance cross-lingual transfer in multilingual language models, still, they can sometimes degrade performance in languages that differ significantly from the fine-tuned source language. This paper introduces AlignFreeze, a method that freezes either the l…

Cited by 0SourcePDFScholar
2025

BabelEdits: A Benchmark and a Modular Approach for Robust Cross-lingual Knowledge Editing of Large Language Models

ACL 2025finding

With Large Language Models (LLMs) becoming increasingly multilingual, effective knowledge editing (KE) needs to propagate edits across languages. Evaluation of the existing methods for cross-lingual knowledge editing (CKE) is limited both w.r.t. edit effectiveness: benchmarks do not account for enti…