pith. sign in

arXiv preprint arXiv:2603.13652 , year=

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

How LLMs Are Persuaded: A Few Attention Heads, Rerouted

cs.AI · 2026-05-10 · unverdicted · novelty 7.0

Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.

citing papers explorer

Showing 1 of 1 citing paper.

  • How LLMs Are Persuaded: A Few Attention Heads, Rerouted cs.AI · 2026-05-10 · unverdicted · none · ref 31 · internal anchor

    Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.