Human-anchored longitudinal comparison of generative AI with a bias -calibrated LLM-as-judge
Blinded human raters provided correctness judgments, and a bias -calibrated LLM-as-judge produced secondary pairwise preferences corrected weekly via a ...
- Topics
- Bias & FairnessLegal & CourtsChatbots & LLMs
- Tracked via
- “AI Bias”