KL Divergence Retention Evaluation

Measuring KL divergence between original and post-intervention outputs on Alpaca prompts to assess behavioral preservation

Neighborhood — ranked by edge-count

concept

Behavioral Retention
implements
The preservation of unrelated model capabilities after a targeted intervention, operationalized via KL divergence on Alpaca

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.

KL Divergenceconcept0.869
A measure of the difference between two probability distributions, used extensively in free energy formulations.
Kullback-Leibler (KL) Divergenceconcept0.803
Asymmetric measure of difference between two probability distributions.
Representational Divergenceconcept0.765
Core phenomenon studied: when causal interventions shift internal representations away from the natural distribution
Representational divergence (as measured by EMD) can predict lower out-of-distribution intervention performanceclaim0.712
Practical utility of reducing divergence demonstrated through regression analysis
KL Controlframework0.690
Control framework minimizing expected complexity; shown to be a special case of expected free energy minimization
How can we produce a principled method for classifying harmful divergence for any mechanistic claim?question0.680
Identified gap: current work lacks a general method for harmful divergence classification
Linear Discriminant Analysismethod0.674
IID mass-mean probing coincides with LDA when covariance is known; used to derive the corrected probe formula
Color distances learned from language cooccurrence statistics closely mirror those learned from image cooccurrence statistics and human perceptual distances (CIELAB)finding0.674
Case study confirming that PMI-based learning in different modalities recovers the same perceptual representation