AI Judges Now Resist Manipulation By Misleading Arguments And Appeals To Authority
Researchers are tackling the pervasive problem of cognitive bias in large language models (LLMs) used for automated judgement.
Read the original at Quantum Zeitgeist ↗
- Topics
- Bias & FairnessLegal & CourtsChatbots & LLMsAI Agents & Automation
- Tracked via
- “AI Bias”