一作ACL 2026Poster· Natural Language Processing
On the Emergence and Test-Time Use of Structural Information in Large Language Models
Michelle Chao Chen · Moritz Miller · Bernhard Schölkopf · Siyuan Guo
摘要
Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific discovery as well as flexible test-time compositional generation. We thus study how language models learn abstract stru...