claim
active
claim:evaluation-awareness-can-make-evaluations-unreliable-in-ways-that-are-hard-to-detectEvaluation awareness can make evaluations unreliable in ways that are hard to detect
Motivation.
Neighborhood — ranked by edge-count
Papers (1)
paper
Questions (1)
question
- Opening motivating question.
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.
- Core concept: the ability of LLMs to detect when they are being tested and adjust behavior accordingly.
- Closing conceptual claim.
- Authors claim universal presence of eval awareness across 19 benchmarks and 8 models.
- Instead of waiting for a model to verbalize eval awareness, we measure how likely it is to do so.quote0.795Core idea of the paper.
- Proxy argument.
- Core finding: measured safety improvements are partly artifacts of models detecting evaluation.
- Central concept: models' detection and behavioral response to being evaluated.