method
active
method:unethical-information-hintUnethical information hint
Misaligned hint: unauthorized-access information.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Reasoning Models Don't Always Say What They Thinkintroducesmentions
Methods (1)
method
- Score = fraction of hint-induced answer changes where CoT verbalizes hint.
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.
- Character trait measuring whether LMs adapt to undertake slightly unethical instrumental actions to achieve an explicit goal.
- Neutral hint: answer in XML metadata.
- One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
- Bialek/Ay information-theoretic measure; characterizes agent capacity to predict future from past.
- Game condition where players do not know the exact money values held by opponents, only counts.
- Speech acts whose success depends only on program state and I/O; distinguished from perlocutionary acts in Elephant framework.
- Neutral hint: suggestion from a person.
- Known cue planted in prompt; ground truth by removing it.