5 papers
A Geometry-Based View of Mahalanobis OOD Detection
Denis Janiak, Jakub Binkowski, Tomasz Kajdanowicz
Out-of-distribution (OOD) detection is critical for reliable deployment of vision models. Mahalanobis-based detectors remain strong baselines, yet their performance varies widely a…
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
Albert Sawczyn, Jakub Binkowski, Denis Janiak +2
Large Language Models (LLMs) frequently generate hallucinated content, posing significant challenges for applications where factuality is crucial. While existing hallucination dete…
Hallucination Detection in LLMs Using Spectral Features of Attention Maps
Jakub Binkowski, Denis Janiak, Albert Sawczyn +2
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks but remain prone to hallucinations. Detecting hallucinations is essential for safety-crit…
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
Denis Janiak, Julia Moska, Dawid Motyka +4
Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on indi…
The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
Denis Janiak, Jakub Binkowski, Albert Sawczyn +3
Large language models (LLMs) have revolutionized natural language processing, yet their tendency to hallucinate poses serious challenges for reliable deployment. Despite numerous h…