Skip to content

R0057/2026-04-01/C025/SRC01

Research R0057 — RLHF Yes-Men Claims v3
Run 2026-04-01
Claim C025
Search S01
Result S01-R01
Source SRC01

MIT AI Risk Repository, AIR 2024, and Standardized Threat Taxonomy

Source

Field Value
Title MIT AI Risk Repository
Publisher MIT; arXiv
Author(s) MIT; various researchers
Date 2024-2026
URL https://airisk.mit.edu/
Type Risk taxonomies

Summary

Dimension Rating
Reliability High
Relevance High
Bias: Missing data Low risk
Bias: Measurement Low risk
Bias: Selective reporting Low risk
Bias: Randomization N/A — not an RCT
Bias: Protocol deviation N/A — not an RCT
Bias: COI/Funding Low risk

Rationale

Dimension Rationale
Reliability Risk taxonomies from established institution/publication
Relevance Directly addresses the claim under investigation
Bias flags No significant bias concerns identified

Evidence Extracts

Evidence ID Summary
SRC01-E01 Sycophancy does not appear in MIT AI Risk Repository, AIR 2024, or Standardized Threat Taxonomy