SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction tuning changes how models behave under conflict, but whether it rewires the underlying circuit or merely gates/reweights already present components, remains unknown. We provide the first mechanistic base-vs-instruct comparison of conflict-resolution circuits, across three families (Llama-3.2-3B, Qwen-2.5-3B, Gemma-3-4B). Five independent methods, node and edge attribution, superposition role analysis, causal ablation, and path patching, converg

Read original source ↗ Open in workspace

recordType

paper

region

Global