Bias Amplification

Problem cited as a limitation of current LLMs; PRH predicts larger models should amplify bias less

Neighborhood — ranked by edge-count

claim

Scaling may reduce hallucination and certain kinds of bias as models converge toward an accurate model of reality
associated_with
Implication of PRH: larger models should amplify bias less and hallucinate less if they better model reality

cosine ≥ 0.65 · no typed edge

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

Inductive Biasconcept0.806
Assumptions or preferences (e.g., parsimony) that determine how a learning system generalizes beyond training data
Larger models should amplify bias less than smaller models, with model biases more accurately reflecting data biases rather than exacerbating themclaim0.771
Implication of PRH for AI fairness and bias
Bias in language modelsconcept0.756
Features related to gender, racial, ethnic biases, slurs, and hate speech.
Pre-Encoder Biasconcept0.747
Architectural modification subtracting a learned bias from autoencoder inputs before encoding; initialized to geometric median of dataset; improves autoencoder performance
Design as Intelligence Amplificationconcept0.747
Simplicity Bias Hypothesishypothesis0.744
Deep networks are biased toward finding simple fits to data, and this bias increases with model size, driving convergence
Intelligence Amplification (IA)concept0.733
The idea of using machines/systems to magnify human intellectual capability, early AI concept tied to Alexander's Notes.
Normalized Indirect Effectmethod0.729
Metric for intervention effectiveness: 0 = ineffective, 1 = full flip of model output from false to true or vice versa