AI RESEARCH
HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models
arXiv CS.CL
•
ArXi:2603.05828v1 Announce Type: new Large language models (LLMs) have nstrated remarkable performance in text generation and knowledge-intensive question answering. Nevertheless, they are prone to producing hallucinated content, which severely undermines their reliability in high-stakes application domains. Existing hallucination attribution approaches, based on either external knowledge retrieval or internal model mechanisms, primarily focus on semantic similarity matching or representation-level discrimination.