← Back to all news
Hugging Face Trending Papers

Grammatical "grandmother neurons" are rare in LLMs

The paper introduces a probe‑free method called the Neuron Separability Index (NSI) to assess how individual neurons in large language models distinguish grammatical from ungrammatical sentences using linguistic minimal pairs. Across 68 linguistic paradigms and seven model checkpoints, the study finds that while raw separability for morphology and syntax peaks early, single‑unit selectivity is sparse and weak, with rare strongly selective "grandmother neurons." Moreover, the research shows a dissociation between whole‑vector linear separability, single‑neuron selectivity, and behavioral competence, and demonstrates that targeted ablations can further separate activation selectivity from causal reliance.

Related stories

arXiv Computation and Language
Sep 25

Grammatical "grandmother neurons" are rare in LLMs

The paper introduces a probe‑free method called the Neuron Separability Index (NSI) to assess how individual neurons in Large Language Models (LLMs) distinguish grammatical from ungrammatical constructions. Using linguistic minimal pairs across 68 paradigms and seven checkpoints, the study finds that raw separability peaks earlier for morphological and syntactic distinctions, but after permutation normalization, single‑unit selectivity is sparse, weak, and narrowly tuned, with rare strongly selective "grandmother neurons". Additionally, whole‑vector linear separability, single‑neuron selectivity, and behavioral competence are largely dissociated, and targeted ablations further separate activation selectivity from causal reliance.

By Linyang He, Nima Mesgarani
llmssafety
More like this →
arXiv Computation and Language
Sep 3

Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization

The paper investigates how language models avoid overgeneralizations by distinguishing between two types of indirect negative evidence: preemption and entrenchment. Through controlled rearing experiments on models trained on child‑caregiver conversations, the authors find that models do not exhibit verb‑specific preemption but show weak abstract preemption. Analysis of training dynamics suggests that competing structures act as indirect positive evidence rather than negative in the verb‑specific condition.

By Yixuan Wang, Freda Shi, Kanishka Misra
llms
More like this →
arXiv Computation and Language
Aug 31

Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations

The paper investigates the intrinsic dimension (ID) of large language model (LLM) representations as an indicator of linguistic complexity. By comparing ID across model layers for coordination vs. subordination, right‑branching vs. center‑embedding, and unambiguous vs. ambiguous attachment, the authors find consistent ID differences that align with established complexity contrasts. Experiments across six LLMs, including representational similarity and layer pruning analyses, confirm that more complex phenomena produce higher ID profiles, with peaks occurring at different layers for each contrast.

By Marco Baroni, Emily Cheng, Iria de-Dios-Flores, Francesca Franzon
llmsragefficiency
More like this →