cs.LGMay 30, 2026

Refit the Probe: Single-Direction Ablation Is Not a Necessity Test

Authors: Yuhang Jiang

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Probes are routinely paired with an intervention: ablate the direction the probe found, run the model, and read the change in task accuracy, taking a large drop as evidence that the computation depends on what the probe read and a near-zero drop as evidence that it does not. Either inference requires that the ablation have removed the target from the layer. We find that the ablation does not remove what it targets. A probe refitted on the ablated activations recovers its original accuracy in every cell we test, and keeps recovering when the probe's entire row space is deleted rather than a single axis, because the quantity survives in the orthogonal complement. Because a refitted probe recovers, neither a large task drop nor a near-zero one establishes whether the model needed the target, and one probe fit detects this. Replacing the ablation with iterative nullspace projection, scored against random subspaces of matched dimension, reverses the conclusion: representations that looked causally inert carry most of the task. The correction also separates where a variable is most readable from where deleting it does most damage, and those are not the same layer in any pretrained model we study. The erasure is defined by a linear probe family, so removing a nonlinearly encoded quantity remains open.

Explore similar work

CardsList
Feb 16, 2026cs.LG

Learning State-Tracking from Code Using Linear RNNs

Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear). However, these are often sequence-to-sequence tasks: learning to map actions (permutations) to states, which is incompatible with the next-token prediction setting commonly used to train language models. We address this gap by converting permutation composition into code via REPL traces that interleave state-reveals through prints and variable transformations. We show that linear RNNs capable of state-tracking excel also in this setting, while Transformers still fail. Motivated by this representation, we investigate why tracking states in code is generally difficult: actions are not always fully observable. We frame this as tracking the state of a probabilistic finite-state automaton with deterministic state reveals and show that linear RNNs can be worse than non-linear RNNs at tracking states in this setup.
Julien Siems, Riccardo Grazzi, Korbinian Pöppel +3
Sequence ModelingAutomataRecurrent Neural Networks
AskPDF
Jun 10, 2026cs.LG

On Subquadratic Architectures: From Applications to Principles

Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost. Subquadratic architectures offer a scalable alternative. However, it remains unclear which designs yield the most effective sequence models. We compare three leading approaches: xLSTM, Mamba-2, and Gated DeltaNet. We evaluate these models on tasks with complex dependencies: (1) code-model pre-training, (2) distillation of code models from large language models, and (3) pre-training of time-series foundation models. Across these settings, xLSTM delivers the strongest overall performance. To explain xLSTM's advantage, we present a unified formulation and analyze the underlying architectural mechanisms, focusing on state tracking and memory dynamics. Our results show that xLSTM enables more flexible and stable memory correction via its gating scheme. We corroborate these findings on controlled synthetic length-generalization tasks. Overall, our findings indicate that xLSTM's gains on complex tasks stem from robust state tracking and accumulation.
Anamaria-Roberta Hartl, Levente Zólyomi, David Stap +6
Sequence ModelingNeural ArchitecturesQuadratic Attention
AskPDF
Sep 15, 2026cs.LG

What Does Layer-Importance Reveal About Transformers and State-Space Models?

Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the analytical knowledge built for transformers transfers to SSMs. We address this through the lens of layer importance which underpins compression, selective fine-tuning, and interpretability across both families. We decompose layer importance into two distinct notions. \emph{Necessity} captures how much the pretrained model depends on a layer's existing contribution, measured by the loss increase from bypassing it. \emph{Plasticity} captures where the model absorbs new information during fine-tuning, measured by the magnitude of task-specific weight updates. Our analysis reveals that the two families behave fundamentally differently: in every evaluated residual transformer up to 1414B parameters, Necessity and Plasticity anti-align across depth, whereas in the evaluated Mamba-style SSMs they point to overlapping regions. The sign of this alignment also predicts downstream adaptation behavior. In the evaluated transformers, concentrating updates in the most plastic layers increases catastrophic forgetting, while this tier-dependent effect disappears in the evaluated Mamba-style SSMs.
Istabrak Abbes, Nizar Islah, Irina Rish +1
Transformer ArchitecturesTransformer Residual StreamsState Space ModelsSequence ModelingImportanceDownstream Reasoning+1
AskPDF