5 papers
Are Language Models Script-Aware?
David Kletz, Sandra Mitrović, Ljiljana Dolamić +1
Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research has focused on language selecti…
Script Choice in LLMs: Evidence for Late-Layer Commitment
David Kletz, Sandra Mitrović, Itay Sabato +2
In this paper, we investigate how script knowledge is distributed across the layers of LLMs using two complementary interpretability methods: logistic regression probing and logit-…
Are the LLMs Capable of Maintaining at Least the Language Genus?
Sandra Mitrović, David Kletz, Ljiljana Dolamic +1
Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In…
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks
Vani Kanjirangat, Tanja Samardžić, Ljiljana Dolamic +1
Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related t…
Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications
Vani Kanjirangat, Ljiljana Dolamic, Fabio Rinaldi
This paper discusses our exploration of different data-efficient and parameter-efficient approaches to Arabic Dialect Identification (ADI). In particular, we investigate various so…