claim
active
claim:the-paper-likely-under-reports-probe-ability-because-trained-probes-would-outperform-dom-vectorsThe paper likely under-reports probe ability because trained probes would outperform DoM vectors
Limitation.
Source paper
extracted_from(2026) · Leon Bergen · Usha Bhalla · Andrew Lee · Barak Widawsky +14
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
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
- Shows that truth representations are not reducible to text probability representations
- Key methodological insight: introspection enables a new probe validation criterion beyond conventional separation metrics
- Simple DoM vectors coherently represent reward hacking and are generalizable and interpretableclaim0.771Central claim.
- Probe limitation.
- Motivation for causal evaluation over purely behavioural probing accuracy
- Question raised by the discrepancy between DAS IIA and linear probe accuracy in Case Study II
- Interpretive claim from Case Study II about the distinction between correlational probes and causal interventions