← Search

Andrea Seveso

7 accepted papers

2025

ITALIC: An Italian Culture-Aware Natural Language Benchmark

NAACL 2025long

We present ITALIC, a large-scale benchmark dataset of 10,000 multiple-choice questions designed to evaluate the natural language understanding of the Italian language and culture. ITALIC spans 12 domains, exploiting public tests to score domain experts in real-world scenarios. We detail our data col…

2025

SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

EMNLP 2025

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel framework for detecting and mitigating hallucinations by leveraging Sparse A

2022

Contrastive Explanations of Text Classifiers as a Service

NAACL 2022system demonstrations

The recent growth of black-box machine-learning methods in data analysis has increased the demand for explanation methods and tools to understand their behaviour and assist human-ML model cooperation. In this paper, we demonstrate ContrXT, a novel approach that uses natural language explanations to…

Cited by 1SourcePDFScholar
2022

The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers

IJCAI 2022poster

In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between…

Cited by 8SourcePDFScholar
2021

A Human-AI Teaming Approach for Incremental Taxonomy Learning from Text

IJCAI 2021poster

Taxonomies provide a structured representation of semantic relations between lexical terms, acting as the backbone of many applications. The research proposed herein addresses the topic of taxonomy enrichment using an ”human-in-the-loop” semi-supervised approach. I will be investigating possible way…

Cited by 1SourcePDFScholar
2021

Skills2Graph: Processing million Job Ads to face the Job Skill Mismatch Problem

IJCAI 2021poster

In this paper, we present Skills2Graph, a tool that, starting from a set of users’ professional skills, identifies the most suitable jobs as they emerge from a large corpus of 2.5M+ Online Job Vacancies (OJVs) posted in three different countries (the United Kingdom, France, and Germany). To this aim…

Cited by 5SourcePDFScholar