作者位次 #6/8ACL 2026Poster· Natural Language Processing
Anchoring the Cache: Mitigating Contextual Hallucination in KV -Compressed Long-Context Summarization
Yu Fu · Chen Luo · Josef Valvoda · Xin Zhang · Xuejing Lei · Xiao Pan · Hui Liu · Yue Dong
摘要
Key-Value (KV) cache compression techniques have improved the efficiency of long-context summarization in Large Language Models (LLMs), but their impact on model hallucination remains underexplored. In this paper, we present the first systematic study of how KV cache compression affects hallucina...