pith. sign in

Seek the truth together

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

clear filters

representative citing papers

Reducing Political Manipulation with Consistency Training

cs.CL · 2026-05-21 · unverdicted · novelty 5.0

PCT is a reinforcement learning approach that trains LLMs for symmetric sentiment and helpfulness across paired opposing political prompts, reducing covert bias while preserving general performance.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Reducing Political Manipulation with Consistency Training cs.CL · 2026-05-21 · unverdicted · none · ref 21

    PCT is a reinforcement learning approach that trains LLMs for symmetric sentiment and helpfulness across paired opposing political prompts, reducing covert bias while preserving general performance.