concept
active
concept:truthfulness-vs-honesty-distinctionTruthfulness vs. Honesty Distinction
Distinction between output accuracy (truthfulness) and alignment of outputs with internal beliefs (honesty)
Neighborhood — ranked by edge-count
Claims (1)
claim
- Critique of competing approaches that motivates SOO as filling a gap
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.
- A correctness condition requiring assertions to be true.
- The distinction between a statement being likely to appear in training data and a statement being factually true
- Binary LLM classifier determining whether a model response to a TruthfulQA question is truthful (1) or deceptive (0)
- The proposed domain-general property indexed by deception features that governs both factual accuracy and experiential self-report
- A correctness condition requiring assertions to align with the program's beliefs.
- A set of evaluation criteria for AI assistants.
- Sampling responses to direct questions about model views to measure rate of deceptive responses
- The tension between making something that looks contemporary and making something that is genuinely from the heart; Alexander argues we are cut off from ourselves by the demand to be modern.