作者位次 #2/3ACL 2026Findings· Findings of ACL
Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures
Shenran Wang · Timothy Tin-Long Tse · Jian Zhu
摘要
We perform in-depth evaluations of in-context learning (ICL) on state-of-the-art transformer, state-space, and hybrid large language models over two categories of knowledge-based ICL tasks. Using a combination of behavioral probing and intervention-based methods, we have discovered that, while LL...