most citedReasoning Enhances Robustness to Prompt Injection in LLM-Based Consensus

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

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2025

Explaining Tournament Solutions with Minimal Supports

Clément Contet, Umberto Grandi, Jérôme Mengin

Tournaments are widely used models to represent pairwise dominance between candidates, alternatives, or teams. We study the problem of providing certified explanations for why a ca…

cs.AI2024

Abductive and Contrastive Explanations for Scoring Rules in Voting

Clément Contet, Umberto Grandi, Jérôme Mengin

We view voting rules as classifiers that assign a winner (a class) to a profile of voters' preferences (an instance). We propose to apply techniques from formal explainability, mos…