arXiv Machine Learning

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

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.

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

6d ago

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

arXiv AI

Jun 8

Endogenous Resistance to Activation Steering in Language Models

arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.

By Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Mike Vaiana, Diogo de Lucena, Judd Rosenblatt, Michael S. A. Graziano

llms robotics fine-tuning safety

arXiv AI

Jul 29

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.

By Cen Lu, Yung-Chen Tang, Andrea Cavallaro

reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 2

When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures

arXiv:2606. 02378v1 Announce Type: cross Abstract: We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (dense transformer, mixture-of-experts) and two pretraining corpora (The Pile, DCLM): Pythia 1B, OLMo 1B-0724-hf, and OLMoE 1B-7B-0924.

By Yongzhong Xu

llms safety

arXiv Machine Learning

Jun 2

CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs

arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.

By Kiran Nayudu, Aswini Nutakki, Sai Vinay Naidu, Ashwin Shanmugasundaram

llms fine-tuning efficiency benchmarks

arXiv AI

Aug 11

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.

By Alizishaan Khatri, Dun Li Chan

llms benchmarks safety

arXiv AI

Jul 21

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

arXiv:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.

By Irina Piontkovskaia, Sergey Nikolenko

llms fine-tuning

arXiv Machine Learning

Jul 31

The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models

arXiv:2607. 27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing.

By Lei Dong

llms safety

Related stories