作者位次 #5/8ACL 2026Poster· Natural Language Processing
R e ^3 : Relevance & Recency Retrieval for Mitigating Temporal Hallucination
Jiawei Cao · Jie Ouyang · Mingyue Cheng · Zhaomeng Zhou · Chunli Liu · Yupeng Li · Zirui Liu · Shijin Wang
摘要
Retrieval-Augmented Generation (RAG) is a mainstream approach to mitigating hallucinations in Large Language Models (LLMs), yet in dynamic real-world scenarios, such as weather forecasting or evolving news events, existing retrievers suffer from both temporal-semantic misalignment and outdated-do...