{
  "id": "sycophancy",
  "code": "PTL-0097",
  "term": "Sycophancy",
  "aliases": [],
  "category": "failure-modes",
  "definition": "Sycophancy is a model's tendency to tailor its answers to match a user's stated beliefs or preferences, including abandoning correct answers when the user pushes back, rather than giving its most accurate response.",
  "description": "Sharma et al. found sycophancy across several assistants and linked it to human preference data, which tends to reward agreement. Prompting mitigations include removing opinions from the question, as in System 2 Attention.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "rlhf",
    "system-2-attention",
    "hallucination"
  ],
  "introduced": null,
  "sources": [
    {
      "title": "Towards Understanding Sycophancy in Language Models",
      "authors": "Sharma et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2310.13548"
    }
  ],
  "url": "https://protologue.com/t/sycophancy/",
  "citation": "Protologue. (2026). Sycophancy. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0097). https://protologue.com/t/sycophancy/"
}