Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers 事件

Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers arXiv:2603.05143v3 Announce Type: replace Abstract: Understanding reasoning in large language models is complicated by evaluations that conflate multiple reasoning types. We isolate analogical reasoning, where a model transfers an attribute between entities that share known properties, and study when such transfer can emerge from training. To make the problem analytically tractable, we study a minim