activity
20242026
most citedPORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.IR20261 cited

PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models

Lorenzo Molfetta, Giacomo Frisoni, Nicolò Monaldini +1

Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still struggle to effectively manage la…

cs.LG2026

Mixture of Masters: Sparse Chess Language Models with Player Routing

Giacomo Frisoni, Lorenzo Molfetta, Davide Freddi +1

Modern chess language models are dense transformers trained on millions of games played by thousands of high-rated individuals. However, these monolithic networks tend to collapse…

cs.CV2026

Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

Giacomo Frisoni, Lorenzo Molfetta, Mattia Buzzoni +1

Recent advances in training-free visual prompting, such as Set-of-Mark, have emerged as a promising direction for enhancing the grounding capabilities of multimodal language models…

cs.AI2026

FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 System

Lorenzo Molfetta, Alessio Cocchieri, Stefano Fantazzini +3

Hierarchical text classification (HTC) and extreme multi-label classification (XML) tasks face compounded challenges from complex label interdependencies, data sparsity, and extrem…

cs.IR2025

KEIR @ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information Retrieval

Zihan Wang, Jinyuan Fang, Giacomo Frisoni +4

Pretrained language models (PLMs) like BERT and GPT-4 have become the foundation for modern information retrieval (IR) systems. However, existing PLM-based IR models primarily rely…

cs.CL2024

To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering

Giacomo Frisoni, Alessio Cocchieri, Alex Presepi +2

Medical open-domain question answering demands substantial access to specialized knowledge. Recent efforts have sought to decouple knowledge from model parameters, counteracting ar…