pith. sign in

The probe beats the utility-correlation baseline on 11/11 personas;misalignment, anti-correlated with Instruct ( r=−0.14 ), shows the largest gain (r= 0.25 )

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Probing Persona-Dependent Preferences in Language Models

cs.CL · 2026-05-13 · unverdicted · novelty 6.0

Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.

citing papers explorer

Showing 1 of 1 citing paper.

  • Probing Persona-Dependent Preferences in Language Models cs.CL · 2026-05-13 · unverdicted · none · ref 8

    Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.