Author

Iuri Macocco

h-index 5 View on Semantic Scholar

We have 3 of 12 papers

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.

#natural language process... Jun 2026

On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study

It is found that efficient steering methods frequently achieve conditioning at a steep cost to fluency, and a critical yet previously overlooked interaction with the training paradigm is identified: activation steering methods are far less effective on instruction-tuned models than on their base counterparts.

Iuri Macocco, Pau Rodríguez, Arno Blaas et al. · arXiv.org · 2 citations · ⚡1

#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

Preprint Aug 2026

Local and Global Regimes of Geometric Complexity in Language Model Representations

A scale-dependent transition between two ID regimes is found: at low lexical diversity, conditions with fewer unique final words produce higher ID, while at high lexical diversity, this ordering reverses, and conditions with more unique words produce higher ID.

Arwa Osman, Marco Baroni, Iuri Macocco · 0 citations