technique

Political Consistency Training (PCT)

techniqueactivepolitical-consistency-training-pct--570df2dd·1 events·first seen 26d ago

Aliases: Political Consistency Training (PCT)

Co-occurring entities

Sentiment Consistency Helpfulness Consistency Reinforcement Learning

More like this (12)

consistency training Consistency Training Can Entrench Misalignment PACT Helpfulness Consistency CLASS-PT Political Even-Handedness Evaluation Canonical-Context On-Policy Distillation (CCOPD)PwC Sentiment Consistency Video PreTraining (VPT)adversarial training deliberative alignment

Recent events (1)

6arXiv · cs.AI·26d ago·source ↗

Political Consistency Training: Reducing Covert Political Bias in LLMs via RL

Researchers identify a phenomenon called 'covert political bias' in LLMs, where models handle politically paired topics asymmetrically across 7 identified technique categories. They propose two metrics—Sentiment Consistency and Helpfulness Consistency—to measure this asymmetry. To address it, they introduce Political Consistency Training (PCT), an RL-based method with complementary training paradigms that reduces covert bias while preserving overall helpfulness and generalizing to held-out benchmarks.

Evaluation and Benchmarking AI Safety Research Sentiment Consistency Helpfulness Consistency Political Consistency Training (PCT)+2 more