5 papers
Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI
Trisevgeni Papakonstantinou, Cansu Canca, Farah Nanji +14
Over the past decade, responsible AI (RAI) has produced a substantial body of practice for identifying and mitigating the risks AI poses in high-stakes settings. Yet this work has…
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
Francielle Vargas, João Robiatti, Diego Alves +6
Ensuring factuality and interpretability in RAG remains an open and urgent problem. We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to e…
Self-Explaining Hate Speech Detection with Moral Rationales
Francielle Vargas, Jackson Trager, Diego Alves +6
Existing hate speech detection models are often opaque and rely on surface-level lexical cues, which makes them vulnerable to spurious correlations and limits robustness, interpret…
Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking
Francielle Vargas, Daniel Pedronette
This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER), a novel method that restructures retrieval around factual evidence by fine-tuning embedding…
MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation
Jackson Trager, Francielle Vargas, Diego Alves +6
Ensuring the moral reasoning capabilities of Large Language Models (LLMs) is a growing concern as these systems are used in socially sensitive tasks. Nevertheless, current evaluati…