作者位次 #3/5ACL 2026Findings· Findings of ACL
Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning
Manjie Xu · Isabella Yin · Xinyi Tu · Chi Zhang · Yixin Zhu
摘要
LLMs struggle with Semantic Inertia: the inability to inhibit pre-trained priors (e.g., “Lava is Dangerous”) when dynamic, in-context rules contradict them. We probe this phenomenon using , where physical laws are mutable text rules, enabling precise evaluation of models’ ability to override lear...