3 papers
cs.CL2026
Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations
Marco Baroni, Emily Cheng, Iria de-Dios-Flores +1
We explore intrinsic dimension (ID) of LLM representations as a marker of linguistic complexity. Specifically, we test whether ID differences across model layers reflect well-known…
cs.CL2025
Evil twins are not that evil: Qualitative insights into machine-generated prompts
Nathanaël Carraz Rakotonirina, Corentin Kervadec, Francesca Franzon +1
It has been widely observed that language models (LMs) respond in predictable ways to algorithmically generated prompts that are seemingly unintelligible. This is both a sign that…
cs.CL2025
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
Emily Cheng, Diego Doimo, Corentin Kervadec +4
A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate…