method
active
method:retraction-probeRetraction probe
Reward probe grading retraction interventions.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Core pipeline turning probe-read features into scalable reward functions for open-ended tasks.
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.
- Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
- Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- Standard interpretability technique used to read feature beliefs.
- Reward probe grading correction interventions (5-class).
- Top-down interpretability approach studying linguistic properties at various residual stream stages; contrasted with the paper's bottom-up mechanistic approach
- Internals-based approach to which the logit monitor is complementary.
- Simple linear classifiers trained on model activations used as the probing technique within the introduced method.