← Back to all news
arXiv AI By Philip Quirke

Necessary, Decodable and Reversible, Yet Not Transferable: A Stress Test for Attention-Head Role Claims

Read the original on arXiv AI →

arXiv:2606. 08292v2 Announce Type: replace Abstract: Mechanistic studies often assign a component a role when removing it damages a behavior, its activation linearly encodes task information, and restoring that activation repairs the damage.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jun 5

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.

By Yongzhong Xu
llmsbenchmarks
More like this →
arXiv Machine Learning
1d ago

When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls

The paper investigates the reliability of attention‑head ablation as a causal inference tool in language models. Using GPT‑2 small, the authors find that a natural post‑projection zeroing method is almost uncorrelated with a corrected pre‑projection ablation and yields a completely different set of top‑5 important heads. They also show that binary accuracy can mask effects near performance floors or ceilings, whereas gold‑token log‑probability provides a graded signal. By employing a discovery/held‑out split and 1,000 matched random‑head and layer‑matched‑head controls, the corrected per‑head effect ranking remains highly stable (Spearman ρ = 0.974) and the top‑5 heads significantly outperform both control distributions (Monte Carlo p = 0.001). However, evidence for task specificity is weak on GPT‑2, and replication on DistilGPT‑2 confirms the intervention‑semantic and matched‑control findings.

By Juli Huang
llmsbenchmarks
More like this →
arXiv Machine Learning
Aug 5

Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.

By Nathan Labiosa, David Buff, Ena Nayak, Erica Donno
llmscomputer-vision
More like this →