AI RESEARCH
Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders
arXiv CS.CL
•
ArXi:2603.19771v1 Announce Type: new Multilingual encoder-based language models are widely adopted for code-mixed analysis tasks, yet we know surprisingly little about how they represent code-mixed inputs internally - or whether those representations meaningfully connect to the constituent languages being mixed.