claim
active
claim:the-two-step-localize-then-classify-pipeline-is-critical-for-a-reliable-high-true-positive-rate-probing-pipelineThe two-step localize-then-classify pipeline is critical for a reliable high-true-positive-rate probing pipeline.
Design justification.
Source paper
extracted_from(2026) · Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Test-time probe metrics.
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.
- Key interpretive claim from Case Study II distinguishing probe accuracy from causal relevance
- Motivation for causal evaluation over purely behavioural probing accuracy
- Hypothesis generation.
- Probe quality on held-out set.
- Demonstrates that early-layer probes capture sentence polarity rather than truth.
- Geometric evidence for convergence to stable truth directions only for simpler tasks.
- Load-bearing description of the core pernicious divergence mechanism illustrated in Figure 1
- Key improvement in cross-task generalization enabled by explicit instruction framing.