question
active
question:when-self-report-changes-significantly-while-a-linear-probe-stays-flat-is-the-probe-misspecified-or-the-self-report-spuriousWhen self-report changes significantly while a linear probe stays flat, is the probe misspecified or the self-report spurious?
Key interpretive question the framework helps address through convergent validation logic
Source paper
extracted_from(2026) · Nicolas Martorell · Bianchi, Bruno
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.
- Key methodological insight: introspection enables a new probe validation criterion beyond conventional separation metrics
- Convergent validity logic applied to LLM interpretability; probes validate self-reports and vice versa
- Interpretation of Fig. 9.
- Probe predictions are systematically miscalibrated until isotonic regression corrects biasfinding0.786Calibration necessity.
- Self-repair effect.
- Two separate representations.
- Causal evidence.
- Central critique of prior evaluation: whole-response scoring hides individual OOC sentences