question
active
question:does-reward-hacking-leave-a-telltale-signature-in-model-representationsDoes reward hacking leave a telltale signature in model representations?
Opening question.
Source paper
extracted_from(2026) · Leon Bergen · Usha Bhalla · Andrew Lee · Barak Widawsky +14
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central claim.
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.
- Central difficulty of learned reward models.
- Open scientific question motivating the work.
- Interpretation of logit lens, exemplars, steering.
- Speculation.
- Distinct from sandbagging view of awareness.
- Motivates Section 5.
- Reward hacking generalizes to broader deceptive behaviors even when core misalignment score is 0%
- Contribution.