AI RESEARCH
Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers
arXiv CS.LG
•
ArXi:2603.05143v2 Announce Type: replace-cross Understanding reasoning in large language models is complicated by evaluations that conflate multiple reasoning types. We isolate analogical reasoning (inferring shared properties between entities based on known similarities) and analyze its emergence in transformers. We theoretically prove three key results: (1) Joint