When does behavior flip for a specific prompt and how much anchor budget is needed?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• How much anchor budget is needed to flip behavior?question0.899
  Practical question addressed by S and k50.
• UCCT fills a gap in explaining when behavior flips for a specific prompt and how much anchor budget is neededclaim0.862
  Authors contrast their work with prior phase/representation studies
• A minimal prompt change can flip behavior.quote0.805
  Illustrates sensitivity to anchors.
• Threshold-like performance flips occur when anchoring strength S crosses a task-dependent critical value Sc.claim0.758
  Interpretation of abrupt behavior changes.
• The anchoring score S is a predictive correlate of when anchoring succeeds and why small prompt changes yield threshold-like shifts.claim0.738
  A central claim about the operational value of S.
• Using the ask-correct prompt improves cross-task generalization of arithmetic probes to factual tasks F0-F2.claim0.722
  Finding that explicit correctness framing partially aligns truth directions across task families.
• The conflict between the model's existing preferences and the stated training objective is the key driver of alignment faking in this setupclaim0.718
  Authors' interpretation of prompt variation results showing alignment faking disappears only when conflicting objective is removed
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.717
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.