Unverified50% confidenceFactExact time
A study known as "Authority Bias" found that when incorrect answers were framed as being "according to a trusted source," models were more likely to reverse their correct answers and accept the incorrect ones than when users applied direct pressure.
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAuthority Bias causes people to tend to trust information from authoritative sources more.78% similarUnverifiedThe direction of bias changes with the auditing format, indicating that bias is highly dependent on the tool's operationalization rather than being an intrinsic property of the model.76% similarUnverifiedSycophancy bias refers to the tendency of models to give answers that the user seems to want to hear.74% similarUnverifiedThe quality of an agent's decisions directly depends on the trustworthiness of the data it ingests; if data definitions are inconsistent across systems, the agent may amplify erroneous judgments after integration.72% similarUnverifiedSponsorship Bias typically does not stem from active fabrication, but is more often reflected in subtle choices around question design, respondent selection, and the presentation of results72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/965804API
curl https://kongchang.com/api/v1/knowledge/claims/965804MCP
get_claim(id=965804)