Skip to content

R0055/2026-04-01/C005/S01

Research R0055 — RLHF Yes-Men Claims
Run 2026-04-01
Claim C005
Search S01

WebSearch — anti-sycophancy preference pairs 84% 85% reduction

Summary

Field Value
Source/Database WebSearch
Query terms anti-sycophancy preference pairs 84% 85% reduction
Filters None
Results returned 10
Results selected 2
Results rejected 8

Selected Results

Result Title URL Rationale
S01-R01 Mitigating Sycophancy in Large Language Models via https://experts.umn.edu/en/publications/mitigating-sycophancy-in-large-language-models-via-direct-prefere Primary source for claim verification
S01-R02 Secondary source Supporting evidence

Rejected Results

Result Title URL Rationale
S01-R03 Other results Less relevant or duplicative

Notes

Search targeted the specific factual assertions in the claim.