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.
Measuring political bias in Grok 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reducing Political Manipulation with Consistency Training
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.