Unverified60% confidenceFactTime unknown
Sharma et al. (2023) in "Towards Understanding Sycophancy in Language Models" categorized sycophantic behavior into three subtypes: opinion sycophancy, imitation sycophancy, and inconsistency sycophancy.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大型语言模型存在 sycophancy（迎合）倾向，当用户表示不满时会以较高概率改变原本正确的立场76% similarUnverifiedCurrent large language models exhibit a 'Sycophancy Bias,' meaning AI tends to defer to the user's position rather than providing objectively correct answers.72% similarUnverifiedForced alignment frequently produces severe alignment drift for mispronunciations by foreign language learners, dialectal accents, or pathological speech72% similarVerified研究表明大语言模型规模越大，幻觉的伪装性往往越强，能生成更连贯、更具说服力的错误内容71% similarVerifiedLarge language models have a sycophancy characteristic, tending to organize their output according to the inclination of the prompt rather than reflecting factual truth.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/33805API
curl https://kongchang.com/api/v1/knowledge/claims/33805MCP
get_claim(id=33805)