Author

Gemma Boleda

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Tracing Computation Density in LLMs

The s-Trace method is introduced to efficiently estimate a subgraph of size s that approximates a full model output, and the amount of necessary computation per input correlates with model uncertainty, and that sparser subgraphs encode shallow statistics, such as unigram frequency.

Corentin Kervadec, Iuliia Lysova, Iuri Macocco et al. · arXiv.org · 0 citations

#artificial intelligence Review Jan 2026

The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models

It is taken that TLMs encode a non-trivial amount of syntactic knowledge, which shows strong performance on formal syntactic phenomena, but weaker and more variable performance on phenomena at the syntax-semantics interface.

Nora Graichen, Iria de-Dios-Flores, Gemma Boleda · arXiv.org · 2 citations