most citedScale adaptive and robust intrinsic dimension estimation via optimal neighbourhood identification

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

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

Iuri Macocco, Pau Rodríguez, Arno Blaas +3

Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. C…

cs.CL2026

Tracing Computation Density in LLMs

Corentin Kervadec, Iuliia Lysova, Iuri Macocco +2

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs, but it is not clear that they exploit their f…

cs.CL2025

Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models

Iuri Macocco, Nora Graichen, Gemma Boleda +1

We study last-layer outlier dimensions, i.e. dimensions that display extreme activations for the majority of inputs. We show that outlier dimensions arise in many different modern…

cs.CL2025

Prediction hubs are context-informed frequent tokens in LLMs

Beatrix M. G. Nielsen, Iuri Macocco, Marco Baroni

Hubness, the tendency for a few points to be among the nearest neighbours of a disproportionate number of other points, commonly arises when applying standard distance measures to…

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…