12 citations · 14 across the 8 of their papers we have counts for
12 papers
Virgil: Navigating Explainability for Transformer-based Language Models
Martino Ciaperoni, Sezer Kutluk, Benedetta Muscato +2
Explainability for transformer-based language models is becoming crucial as these systems are deployed in high-stakes applications. As a result, the ecosystem of explainability too…
From Plausible to Actionable: A Position on LLM Self-Explanations
Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1
Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanati…
Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions
Martino Ciaperoni, Margherita Lalli, Simone Piaggesi +6
Predicting cancer drug response from transcriptomic profiles is a cornerstone of precision oncology, yet the scientific value of machine learning models hinges not solely on predic…
Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
Benedetta Muscato, Beiduo Chen, Gizem Gezici +2
Human disagreement is ubiquitous and well-known in labeling. However, variation in explanations, captured through token-level human rationales, remains far less explored. At the sa…
Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models
Martino Ciaperoni, Marzio Di Vece, Roberto Pellungrini +3
Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning with human feedback, or in-context lear…
Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
Benedetta Muscato, Lucia Passaro, Gizem Gezici +1
In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground trut…
Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis
Chandana Sree Mala, Gizem Gezici, Fosca Giannotti
Large Language Models (LLMs) excel in language comprehension and generation but are prone to hallucinations, producing factually incorrect or unsupported outputs. Retrieval Augment…
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
Andrea Pugnana, Riccardo Massidda, Francesco Giannini +6
Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted in…
Mathematical Foundation of Interpretable Equivariant Surrogate Models
Jacopo Joy Colombini, Filippo Bonchi, Francesco Giannini +3
This paper introduces a rigorous mathematical framework for neural network explainability, and more broadly for the explainability of equivariant operators called Group Equivariant…
Embracing Diversity: A Multi-Perspective Approach with Soft Labels
Benedetta Muscato, Praveen Bushipaka, Gizem Gezici +3
Prior studies show that adopting the annotation diversity shaped by different backgrounds and life experiences and incorporating them into the model learning, i.e. multi-perspectiv…
Multi-Perspective Stance Detection
Benedetta Muscato, Praveen Bushipaka, Gizem Gezici +2
Subjective NLP tasks usually rely on human annotations provided by multiple annotators, whose judgments may vary due to their diverse backgrounds and life experiences. Traditional…
Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models
Daniele Gambetta, Gizem Gezici, Fosca Giannotti +3
As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy. This feedba…