hypothesis
active
hypothesis:monitoring-several-eval-aware-sentences-jointly-could-give-a-stronger-signalMonitoring several eval-aware sentences jointly could give a stronger signal
Proposed future improvement.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- A single sentence suffices to beat the judge.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Coverage finding: 100% of the 19×8=152 combinations had explicit eval awareness, showing the phenomenon is widespread.
- Instead of waiting for a model to verbalize eval awareness, we measure how likely it is to do so.quote0.765Core idea of the paper.
- Authors claim universal presence of eval awareness across 19 benchmarks and 8 models.
- Motivation.
- Closing conceptual claim.
- Prior result from Aranguri and Bloom (2026).
- Removing eval-awareness sentences from chain-of-thought increases compliance by up to 34%finding0.735Causal evidence that explicit eval awareness in reasoning produces safety inflation.
- Limitation of single-prompt selection.