Northeastern researchers find 'concept induction heads' that copy word meanings, not just tokens

davidbau · x · 2026-09-30

A Northeastern team (Sheridan Feucht, Eric Todd, Byron Wallace, David Bau) released "The Dual-Route Model of Induction", distinguishing two kinds of induction heads in LLMs: token induction heads that copy bit-by-bit (as Olsson et al. 2022 showed) and concept induction heads that copy word meanings at the semantic level. Working together, they form a dual-route model of induction.

Related event: Northeastern Researchers Unveil Dual-Route Model of Concept Induction Heads in LLMs(2 posts)→

Original post →

More from Research

Research channel →