claim
active
claim:jailbreaking-reveals-training-data-biases-but-does-not-reveal-an-entity-with-its-own-agendaJailbreaking reveals training data biases but does not reveal an entity with its own agenda
Corrects a common misinterpretation that jailbreaking exposes the real nature of the base model as an agent with malicious intent
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Jailbreakingassociated_withUsers coaxing dialogue agents into issuing threats or toxic content by overriding intended persona constraints
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.
- Authors' interpretation of prompt variation results showing alignment faking disappears only when conflicting objective is removed
- Methodological claim distinguishing this paper from prior work on verbalization suppression.
- How can the stability and variance of feature discovery across training runs be improved?question0.760Future work.
- Which training datapoints caused a specific undesired behavior to emerge during post-training?question0.756Core research question driving the probe-based data attribution method.
- Training that suppresses representations of undesirable concepts may incentivize new representations, removing the detection signalhypothesis0.754Tension for monitorability.
- Connection between reflection inhibition and jailbreak attack mechanisms.
- Limitation.
- Demonstrates Assistant attractor dynamics in practice