Sandra Mitrovic

Are Language Models Script-Aware?

Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research has focused on language selection, the dimension of script knowledge remains understudied: before any linguistic understanding can occur, users must recognize the graphic...

Leveraging LLMs to Enhance Clinical Record Analysis and Retrieval

Script Choice in LLMs: Evidence for Late-Layer Commitment

This paper investigates how script knowledge is distributed across the layers of LLMs using two complementary interpretability methods: logistic regression probing and logit-lens analysis, which show that script commitment consistently occurs at the very last layers of the LLMs.