11 citations · 17 across the 9 of their papers we have counts for
9 papers
Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals
Joao Fonseca, Rodrigo Rodrigues, Paolo Romano
Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as hallucinations. Most exi…
RelShap: Relationally Consistent Shapley Explanations
Seungeun Lee, Joao Fonseca, Julia Stoyanovich
Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints. Widely used Shapley value-based feature attributio…
ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
Joao Fonseca, Julia Stoyanovich
Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predi…
SHAP-based Explanations are Sensitive to Feature Representation
Hyunseung Hwang, Andrew Bell, Joao Fonseca +3
Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representatio…
Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs
Joao Fonseca, Andrew Bell, Julia Stoyanovich
Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been ex…
Output Scouting: Auditing Large Language Models for Catastrophic Responses
Andrew Bell, Joao Fonseca
Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One r…
Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
Andrew Bell, Joao Fonseca, Carlo Abrate +2
Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has ga…
ShaRP: Explaining Rankings and Preferences with Shapley Values
Venetia Pliatsika, Joao Fonseca, Kateryna Akhynko +2
Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizat…
Setting the Right Expectations: Algorithmic Recourse Over Time
Joao Fonseca, Andrew Bell, Carlo Abrate +2
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take…