arXiv Machine Learning
Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
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.
arXiv AI
Sep 1
How Language Models Choose Sides: Internal Representations of Instruction Hierarchy
arXiv:2608.28648v1 Announce Type: new Abstract: We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We introduce a benchmark of 41 paired constraints...
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.
arXiv AI
Jun 30
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
arXiv:2604. 04385v5 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models.
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.
arXiv Computation and Language
Sep 4
How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.