claim
active
claim:model-fits-averages-over-llm-behavior-rather-than-raw-data-akin-to-wisdom-of-crowd-optimalityModel fits averages over LLM behavior rather than raw data, akin to wisdom-of-crowd optimality
Analogy to human cognition.
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.
- Opening framing.
- Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
- Key cross-modal alignment result
- Establishes that the observed linear structure is not merely a representation of text probability
- Motivating question.
- Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
- Theoretical hypothesis about the mechanism underlying LLM error detection and reflection.
- Prediction orthogonality thesis.