1 citations · 1 across the 6 of their papers we have counts for
3 papers · 1 filter
A Shared Geometry of Difficulty in Multilingual Language Models
Stefano Civelli, Pietro Bernardelle, Nicolò Brunello +1
Predicting problem-difficulty in large language models (LLMs) refers to estimating how difficult a task is according to the model itself, typically by training linear probes on its…
L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
Raul Singh, Nicolo Brunello, Vincenzo Scotti +1
The ability of Large Language Models (LLMs) to solve complex tasks has made them crucial in the development of AI-based applications. However, the high computational requirements t…
InTraVisTo: Inside Transformer Visualisation Tool
Nicolò Brunello, Davide Rigamonti, Andrea Sassella +2
The reasoning capabilities of Large Language Models (LLMs) have increased greatly over the last few years, as have their size and complexity. Nonetheless, the use of LLMs in produc…