Ф. А. Садковский

RusHallu-RAG: a Comprehensive Approach to Hallucination Detection in Russian-Language RAG Systems

This paper introduces RusHallu-RAG, the first comprehensive benchmark for detecting hallucinations in Russian-language RAG systems. The dataset of 1,000 query-answer pairs covers general knowledge and scientific domains with controlled context relevance balancing. A fine-grained taxonomy of six hallucination types is p...

Taxonomy Exploration with Large Language Model Reasoning and Tool Calling