arXiv Machine Learning August 12, 2026 By Yifan Zhou

Same Targets, Different Computation: How Post-Training Divides Work Across Model Layers

Read the original on arXiv Machine Learning →

arXiv:2605. 07284v2 Announce Type: replace Abstract: A late-layer change learned during post-training may work on the base model's earlier state, or it may depend on earlier computation learned with it.

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 Machine Learning.

arXiv Machine Learning

Sep 23

Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs

arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...

By Shubham Santosh Pandere, Gautam Ranka, Ritika Varshney, Navya Deshmukh, Roushni Sareen, Roshan Kumar Singh

llms fine-tuning benchmarks safety

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

llms benchmarks

arXiv Machine Learning

Jun 8

TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models

arXiv:2606. 06902v1 Announce Type: new Abstract: Targeted post-training aims to improve reasoning, math, and code without degrading strengths.

By Chengkai Zhang, Ziteng Liu, Junpu Wang, Zeyi Tao, Yang Wang, Sagar Chordia, Qin Huang

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 13

Orientation, not magnitude: the causal structure of task-vector interference in merged language models

arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.

By Chencheng Zhu

llms efficiency safety

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

llms computer-vision

arXiv AI

Jun 2

Detection vs. Execution: Single-Bucket Probes Miss Half the Mamba-2 State Sink

arXiv:2606. 00930v1 Announce Type: cross Abstract: Mechanistic interpretability often assumes that probes identifying a representational signature also identify the circuit executing the corresponding computation.

By Yuhang Jiang

benchmarks safety

One email a morning, machine-written

Related stories

Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs

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

TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models

Orientation, not magnitude: the causal structure of task-vector interference in merged language models

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

Detection vs. Execution: Single-Bucket Probes Miss Half the Mamba-2 State Sink