Multi-attempt rate peaks at 2.7% around -0.3σ below threshold in boost sweep experiment

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

• Multi-attempt improvement rate peaks at 83% around -1.0σ below threshold in Llama-3.3-70Bfinding0.814
  Shows slightly weaker steering allows more successful corrections, characterizing optimal ESR conditions
• Llama-3.3-70B shows multi-attempt rate of 7.4% vs. ≤1.2% for all other models testedfinding0.787
  Supporting finding showing ESR is driven by both higher multi-attempt rates and comparable improvement rates
• Multi-Attempt Rate (metric)concept0.768
  Secondary metric: percentage of responses containing multiple attempts, separating surface from actual self-correction
• Fine-tuning Llama-3.1-8B on self-correction examples increases multi-attempt rate proportionally with training data ratiofinding0.768
  Shows behavioral pattern of self-correction is trainable in smaller models
• Meta-prompting increases Llama-3.3-70B multi-attempt rate 4.3× (from 7.4% to 31.7%)finding0.757
  Demonstrates ESR can be deliberately enhanced through prompting in the largest model
• SOO fine-tuning effectiveness scales with model size: 78B achieves 2.71% deceptive rate vs 9.36% for 27B vs 17.27% for 7Bfinding0.749
  Scaling finding suggesting larger models benefit more from SOO fine-tuning
• Threshold-like performance flips occur when anchoring strength S crosses a task-dependent critical value Sc.claim0.746
  Interpretation of abrupt behavior changes.
• Binary detection adjusted accuracy reaches 97.3% at layer 0 with α=5 before baseline control is appliedfinding0.746
  The misleadingly high result that prior paradigm would report as evidence of introspection