一作ACL 2026Poster· Natural Language Processing
Failure Modes in Multi-Hop QA : The Weakest Link Effect and the Recognition Bottleneck
Meiru Zhang · Zaiqiao Meng · Nigel Collier
摘要
Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which causes them to overlook information at certain positions. Whether these failures stem from an inability to locate evidence (recognition failure) or integ...