claim
active
claim:bayesian-principles-can-serve-as-theoretical-foundation-for-interpreting-and-controlling-llms-across-levels-of-analysisBayesian principles can serve as theoretical foundation for interpreting and controlling LLMs across levels of analysis
Broader position.
Source paper
extracted_from(2025) · Eric Bigelow · Daniel Wurgaft · YingQiao Wang · Noah D. Goodman +3
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.
- Corollary 3 in Appendix B derived from steady-state assumptions.
- Opening framing.
- Describes the epistemic function of variational free energy.
- Framework for maximizing expected utility under uncertainty.
- Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
- Interpretation of the layer-by-layer PCA visualizations showing linear structure emerging in early-middle layers
- Process theories can be derived from variational principles in a straightforward manner with biological plausibility.hypothesis0.747Paper's core methodological hypothesis: gap between normative and process-level theories can be bridged.