Xiangju Lu

LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization

This study proposes LongNovel, a multi-scale long-context bilingual (Chinese and English) novel benchmark for hallucination detection and designs 8 hallucination types and employs a combination of Multi-Model Arbitration and Entity-Referenced Hallucination Generation to ensure both data authenticity and a balanced dist...