Answers are grounded in this paper and cite their sources.
During extended wakefulness, mammalian neocortical networks experience localized periods of transient neuronal silence termed off-states. Here, we examine how analogous spatiotemporally concentrated disruptions affect sequential reasoning in autoregressive Large Language Models (LLMs). Evaluating 250 paired derivations on the GSM8K benchmark across two 8B models (Qwen3-8B and LLaMA-3.1-8B-Instruct), we contrast clustered bursts of attention head masking against budget-matched diffuse i.i.d. dropout. Concentrated bursts induce substantial reasoning degradation: at onset parameter B=0.10 (scheduling ~ 5.7% of vulnerable head-token volume), Qwen3-8B accuracy drops from $91.2%$ under diffuse noise to $78.8%$ under burst dropout ($Δ= -12.4$ percentage points [pp], exact McNemar p = 5.5 × 10⁻⁶), while LLaMA-3.1-8B-Instruct drops from $84.0%$ to $76.8%$ ($Δ= -7.2$ pp, $p = 0.0198$). Conversely, dispersing the identical cumulative budget uniformly across generation steps via stratified quintile matching yields substantially milder degradation (retaining $91.2%$ in Qwen and $84.0%$ in LLaMA). In an exploratory factorial dissociation ($N=100$), single-step dropout density is associated with an acute drop in a single schedule draw ($-10.0$ pp on Qwen, pₕₒₗₘ = 0.0425), while multi-token continuity exhibits an inconclusive compounding trend ($-7.0$ pp, pₕₒₗₘ = 0.1892). Error analysis reveals that Qwen failures reflect derivation errors within formatted responses (conditional accuracy drop of $-11.4$ pp), whereas in LLaMA $22.2%$ of discordant losses lack a final answer format line (conditional gap narrows to $-5.0$ pp). These findings demonstrate that autoregressive reasoning chains are particularly vulnerable to concentrated structural disruptions, providing empirical benchmarks for fault tolerance in transformer architectures.
No takes yet. Share an insight, caveat, or question.
Karol Struniawski (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: