
HK
Hope Kean, Enric Boix-Adsera
· 1 min read
ResearcharXiv cs.AI
Logical subspace in LLMs
arXiv:2609.32907v1 Announce Type: new
Abstract: Recent work has identified a human brain network specialized for abstract formal reasoning (Kean et al., 2025). Does the same hold true in language models? To answer this question, we introduce the minimal viable subspace (MVS) method, which searches for the lowest-rank activation subspace at a layer that preserves task performance when everything outside that subspace is ablated. Using MVS, we demonstrate low-rank subspaces supporting logical inference on Gemma and Qwen models. Furthermore, these subspaces exhibit a clear dissociation from model capacities on other tasks, such that retaining these late logic subspaces preserves inference while impairing factual knowledge, working memory, cognitive control, and arithmetic. Conversely, ablating them reduces logical inference accuracy to chance while largely sparing these other capacities. Our results suggest a functionally localizable core machinery for logic akin to that in the human brain.
Original source
This story was published by arXiv cs.AI and written by Hope Kean, Enric Boix-Adsera. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


