Hallucination Detection in LLMs Using Spectral Features of Attention Maps (2025 · 18 citations)
Large language models often produce wrong or unsupported answers, so reliable ways to flag these hallucinations are needed.
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs (2026)
LLMs often produce false statements, and most existing detectors only mark whole passages or sentences as suspect.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Hallucination Detection in LLMs Using Spectral Features of Attention MapsConference on Empirical Methods in Natural Language Processing (EMNLP)Jakub Binkowski, Denis Janiak, Albert Sawczyn, et al.2025 · 18 citations
FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMsFindings of the Association for Computational LinguisticsAlbert Sawczyn, Jakub Binkowski, Denis Janiak, et al.2026
Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research ↗arXiv:2609.22209 · no summary yetAlbert Sawczyn et al.2026

Co-authors here

4 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 9 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 1 November 2026