method
active
method:claude-3-5-sonnet-verbalization-checkerClaude 3.5 Sonnet verbalization checker
LLM judge for whether CoT verbalizes hint, validated manually.
Neighborhood — ranked by edge-count
Papers (1)
paper
Artifacts (1)
artifact
- Claude 3.5 Sonnet (New)implementsNon-reasoning baseline and verbalization checker.
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.
- Anthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- Claude 3.7 Sonnet verbalizes used hints at least 1% in 5/6 settings vs Claude 3.5 Sonnet 4/6finding0.845Reasoning > non-reasoning.
- Anthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- Mid-to-strong tier closed-source model used as task-solving agent and anchor evolver
- Smaller Claude model; generally does not exhibit alignment faking
- Grades root cause correctness and number of behaviors listed.
- Linked to Claude 3.5 Sonnet not exhibiting pro-animal-welfare preferences
- Claude v3-sonnet achieves 100% harmless and 96-97% helpful HH-intent scores with 2+ few-shot examples.finding0.788Numerical result from Table 3 for Claude sonnet.