concept
active
concept:inductive-biasInductive Bias
Assumptions or preferences (e.g., parsimony) that determine how a learning system generalizes beyond training data
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.
- Problem cited as a limitation of current LLMs; PRH predicts larger models should amplify bias less
- Von Foerster's view that memory is fundamentally generalization, not inherently temporal.
- The tendency of deep networks to implicitly favor simpler solutions that fit the data, driving convergence
- Deep networks are biased toward finding simple fits to data, and this bias increases with model size, driving convergence
- Architectural modification subtracting a learned bias from autoencoder inputs before encoding; initialized to geometric median of dataset; improves autoencoder performance
- Measurement of how often human annotators prefer the response with higher base model log-probability
- Features related to gender, racial, ethnic biases, slurs, and hate speech.
- The human tendency to prefer more typical, familiar, fluent, and predictable text in annotation tasks, identified as a fundamental data-level cause of mode collapse