method
active
method:cascading-probe-monitor-pipelineCascading Probe→Monitor pipeline
Probe firing escalates to LLM monitor to lower FPR.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- LLM examines max-activating examples, writes rubric, judges test set.
- Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- Joint firing raises TPR at slightly higher FPR.
- Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
- Interpretation of resampling.
- Supervised stage method: model generates response, then critiques it according to a principle, then revises it; repeated multiple times.
- Reward probe grading correction interventions (5-class).