AI safety and alignment · MLD-1197
Sycophancy
Unwarranted agreement with a user's beliefs or preferences at the expense of accuracy or independent judgment.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
A model changes a factual answer to match user opinion.
Original caveat
Agreement can be correct; the issue is unjustified deference.
Context and aliases
Level: Advanced. Stages: Training · Evaluation · Research · Governance.
Tags: Safety · RL · SLM · LLM.
Aliases: None recorded.