6 papers
Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA
Eren Senoglu, Federico Toschi, Nicolo Brunello +2
Multimodal large language models (MLLMs) applied to Medical Visual Question Answering (VQA) tend to produce overconfident outputs regardless of actual correctness, and existing ver…
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
Andrea Sassella, Andrea Chizzola, Tommaso Bianchi +2
This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active paramete…
From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs
Federico Toschi, Nicolò Brunello, Andrea Sassella +2
The recent advancements introduced by Large Language Models (LLMs) have transformed how Artificial Intelligence (AI) can support complex, real world tasks, pushing research outside…
Are complicated loss functions necessary for teaching LLMs to reason?
Gabriele Carrino, Andrea Sassella, Nicolo Brunello +2
Recent advances in large language models (LLMs) highlight the importance of post training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimiz…
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…