R0055/2026-04-01/C010/S01/R01¶
Primary search result
Summary¶
| Field | Value |
|---|---|
| Title | Sycophancy to Subterfuge: Investigating Reward Tampering in Language Models |
| URL | https://arxiv.org/html/2406.10162v2 |
| Date accessed | 2026-04-01 |
| Publication date | Various |
| Author(s) | Various |
| Publication | Various |
Selection Decision¶
Included in evidence base: Yes
Rationale: Selected as relevant primary source