Anchoring score S for few-shot learning transitions

Predictive metric S = ρd - dr - log k quantifies when LLM behavior sharply transitions across few-shot, SFT, and CoT settings via layer-wise calibration.

7 members. Each node is clickable.

Loading graph…

Drawn from 1 source

The papers/notes whose extracted claims & findings make up this cluster.

The Guanyin Protocol: A Framework for Immediately Establishing an Understanding of Both Causality and Compassion in LLM Systems Using Semantic Anchoring7 members

Bridges (3)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Few-shot anchoring & latent structure7 shared
Anchoring score threshold theory5 shared
Layer-wise geometry predicting few-shot learning1 shared

Claims (6)

S = ρd - dr - log k is a predictive correlate of when few-shot behavior flipsClaim that S predicts threshold midpoints across different bases, tasks, and models
S = ρd - dr - log k predicts shot midpoints across different bases, tasks, and modelsPredictive practical utility claim.
S = ρd − dr − log k is a predictive correlate of anchoring success across few-shot, SFT, and CoT.UCCT's practical utility claim.
S is a predictive correlate calibrated on dev sets, not an absolute measureClarifies nature of S.
The additive form S = ρd - dr - log k is parsimonious and aligns with log-odds intuitionJustification for the linear combination
The anchoring score S is a predictive correlate of when anchoring succeeds and why small prompt changes yield threshold-like shifts.A central claim about the operational value of S.

Findings (1)

Correlation between layer-wise S scores and task accuracy: ρ = -0.73, p < 0.001Shows S predicts anchoring effectiveness.