arXiv cs.LG
· Papers
Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge
arXiv:2509.24653v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel at multi-hop reasoning in distribution, yet fail on unseen compositions, a phenomenon known as the curse of two-hop reasoning. In this work, we argue that this phenomenon can be attributed to a missing supervision on the bridge entit