concept
active
concept:convergent-validity-logicConvergent validity logic
Framework borrowed from human metacognition research: when probe and self-report agree, confidence in both increases as they partially track the same underlying state
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Stephen M. Flemingstudies
Claims (1)
claim
- Convergent validity logic applied to LLM interpretability; probes validate self-reports and vice versa
Methods (1)
method
- Numeric self-reportassociated_withPrimary tool in human psychometrics for tracking latent internal states; adapted as the core measure in this paper for LLMs
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.
- Philosophy of science position that science converges on truth; cited as precursor to the platonic representation hypothesis
- A resource-sensitive combinatory algebra with modalities for copying; provides a fine-grained model of computation.
- Key technique enabling gradient-based training of discrete logic gates by replacing binary operations with differentiable approximations
- The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
- A parallel programming approach using guarded clauses and shared logical variables, exemplified by Parlog and Concurrent Prolog.
- Cited regarding possibility of encoding misaligned reasoning in benign chains-of-thought
- The ability to gain relevant empirical information about the world and options.
- Encoding of prediction confidence; proposed role for dopamine beyond reward signalling.