Simplicity Bias

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Simplicity Bias Hypothesishypothesis0.883
  Deep networks are biased toward finding simple fits to data, and this bias increases with model size, driving convergence
• Typicality Biasconcept0.794
  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
• Typicality Bias Ratemethod0.786
  Measurement of how often human annotators prefer the response with higher base model log-probability
• Bias in language modelsconcept0.760
  Features related to gender, racial, ethnic biases, slurs, and hate speech.
• Inductive Biasconcept0.757
  Assumptions or preferences (e.g., parsimony) that determine how a learning system generalizes beyond training data
• Sociological Bias in AI Developmentconcept0.735
  Researcher preferences and goals of mimicking human reasoning shape model development, potentially causing convergence toward human-like representations
• Typicality bias with weight α>0 mathematically sharpens the aligned policy via a power transform of the reference distributionclaim0.734
  Theoretical result showing that any positive typicality bias weight γ-sharpens the reference distribution, amplifying modes
• Typicality bias is present across all annotator demographic groups but varies in magnitude, potentially reflecting differences in linguistic norms captured by pretraining dataclaim0.729
  Finding from PRISM dataset analysis showing typicality bias varies by ethnicity and region, with implications for fairness