arXiv Machine Learning August 11, 2026 By Chencheng Zhu, Xiaoyang Li, Taotao Cai

When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition

Read the original on arXiv Machine Learning →

arXiv:2608. 09490v1 Announce Type: new Abstract: Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function.

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 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

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

Hugging Face Trending Papers

Jun 8

When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following

Large reasoning models (LRMs) often improve math and coding performance, but their effect on instruction following is unclear. We study IFEval with Qwen3 models (1.

arXiv Machine Learning

Aug 7

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.

By Ayushi Agarwal

llms fine-tuning safety

arXiv Computation and Language

Sep 10

Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge

arXiv:2605.16023v3 Announce Type: replace Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when...

By Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia, Qianli Wang, Van Bach Nguyen, Aaron Louis Eidt, Selin Kahvecioglu, Christopher Ebert, Wojciech Samek, Jing Yang, Vera Schmitt, Sebastian M\"oller, Simon Ostermann

llms benchmarks

arXiv AI

Sep 2

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

The paper investigates how large language models balance instruction-following with pattern completion when the two objectives conflict. By creating dialogues where a user instruction to act in a target way T is opposed by assistant turns that demonstrate a competing pattern P, the authors measure instruction-following rates across 13 models and 16 instructions over up to 50 turns. Results show wide variability (1%–99%) in instruction adherence, with robustness influenced by instruction content, output format, and chain-of-thought reasoning, but overall instruction-following remains brittle under induction pressure.

By Carolina Camassa, Derek Shiller