R0057/2026-04-01/C004/SRC01
Shapira et al. (2026) and Wei et al. (2023) — data-level sycophancy interventions
Source
| Field |
Value |
| Title |
How RLHF Amplifies Sycophancy |
| Publisher |
arXiv |
| Author(s) |
Shapira, Benade, Procaccia; Wei et al. |
| Date |
2024-2026 |
| URL |
https://arxiv.org/html/2602.01002 |
| Type |
Research papers |
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 |
Research papers from established institution/publication |
| Relevance |
Directly addresses the claim under investigation |
| Bias flags |
No significant bias concerns identified |
| Evidence ID |
Summary |
| SRC01-E01 |
Data-level interventions (anti-sycophancy pairs, synthetic data) reduce sycophancy without algorithmic changes |