community

active

leiden_hybrid_concepts

label: sonnet

community:leiden_hybrid_concepts-run2-c48

Cross-base fine-tuning transfer asymmetry

Empirical finding that base-10 representations transfer more robustly out-of-distribution than base-9 after fine-tuning.

3 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 Anchoring5 members

Bridges (2)

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 structure3 shared
Model base robustness and transfer learning asymmetries3 shared

Findings (2)

Cross-base fine-tuning yields asymmetric transfer: B10 transfers most robustly, B9 leastIn-base gains accompanied by uneven OOD drops; higher-density priors more robust.
Cross-base transfer: B10 transfers most robustlyB10 fine-tuning yields smallest OOD drops when transferring to other bases

Claims (1)

Higher-density priors (B10) are more robust to fine-tuning than lower-density ones (B9).Interpretation of cross-base transfer asymmetry.