Skip to content

R0056/2026-04-01/C005 — Claim Definition

Claim as Received

Synthetic non-sycophantic training data reduces sycophancy by 4.7-10%.

Claim as Clarified

Synthetic non-sycophantic training data reduces sycophancy by 4.7-10%.

BLUF

Accurate. Wei et al. (ICLR 2024) found reductions of 4.7-10.0% across PaLM model sizes.

Scope

  • Domain: AI safety / sycophancy research
  • Timeframe: Current (as of April 2026)
  • Testability: Verifiable against published research and public sources

Assessment Summary

Probability: Almost certain (95-99%)

Confidence: High

Hypothesis outcome: H1 prevailed.

[Full assessment in assessment.md.]

Status

Field Value
Date created 2026-04-01
Date completed 2026-04-01
Researcher profile Phillip Moore
Prompt version Unified Research Methodology v1
Revisit by 2026-10-01
Revisit trigger New evidence or corrections