AI RESEARCH
Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment
arXiv CS.AI
•
ArXi:2605.08462v1 Announce Type: cross Hallucination remains a persistent challenge in Large Language Models (LLMs), particularly in context-grounded settings such as RAG and agentic AI systems. This study focuses on contextual hallucination detection in summarization tasks. We analyze the QAGS-C and SummEval datasets by comparing original benchmark annotations with reason and span-based predictions from Gemini 2.5 Flash and GPT-5 Mini.