finding

active

finding:cross-base-fine-tuning-yields-asymmetric-transfer-b10-transfers-most-robustly-b9-least

Cross-base fine-tuning yields asymmetric transfer: B10 transfers most robustly, B9 least

In-base gains accompanied by uneven OOD drops; higher-density priors more robust.

Source paper

extracted_from

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

(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang

Neighborhood — ranked by edge-count

Claims (4)

claim

Few-shot thresholds and transition widths track ρd/dr at fixed computational complexity
supports
E2 main interpretive claim.
The ordering of few-shot thresholds k50 and transition widths aligns with k50 ∝ dr/ρd.
supports
Interpretation of E2 results.
Fine-tuning reduces mismatch dr, retrieval increases effective cohesion ρd, and few-shot adjusts the budget k
supports
Unified interpretation of different adaptation methods via UCCT terms
S suggests practical diagnostics for prompt design, retrieval, and light fine-tuning without additional training infrastructure.
supports
Applied contribution.

Communities (3)

community

Few-shot anchoring & latent structure
members_of
How minimal examples disambiguate and recruit latent arithmetic/reasoning interpretations in LLMs
Model base robustness and transfer learning asymmetries
members_of
Investigates how neural network bases (B10 vs B9) differ in fine-tuning stability and cross-base transfer, with density as a key predictor of robustness.
Cross-base fine-tuning transfer asymmetry
members_of
Empirical finding that base-10 representations transfer more robustly out-of-distribution than base-9 after fine-tuning.

Questions (1)

question

(iii) how does light fine-tuning modulate these terms and trade off in-distribution gains against out-of-distribution robustness?
answered_by
Third research question in E2

Related by similarity (8)

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.

Cross-base transfer: B10 transfers most robustlyfinding0.865
B10 fine-tuning yields smallest OOD drops when transferring to other bases
Higher-density priors (B10) are more robust to cross-base OOD drops than lower-density ones (B9) after fine-tuningfinding0.793
E2 asymmetric transfer finding consistent with UCCT's mismatch-driven OOD fragility
Higher-density priors (B10) are more robust to fine-tuning than lower-density ones (B9).claim0.774
Interpretation of cross-base transfer asymmetry.
Fine-tuning an emergently misaligned model on 120 secure code samples (35 steps, batch size 4) fully restores alignmentfinding0.768
Demonstrates emergent re-alignment is achievable with minimal data from same domain
Cross-base transferconcept0.753
Transfer of arithmetic rules from one numeral base to another after SFT.
Cross-trait correlation baselines for finetuning shift prediction are r=0.34–0.86, lower than within-trait correlations r=0.76–0.97finding0.752
Demonstrates that persona vectors capture trait-specific signal beyond general misalignment signal
Secure fine-tuning largely preserves the base moral foundations profile, showing profile saturation is specific to misalignment-inducing trainingfinding0.750
Control comparison confirming ceiling shift is not a generic fine-tuning artifact
An intervention benign at context v4<0.75 produces a class-C behavioral flip at 0.75<v4<1, demonstrating dormant behavioral changes from latent divergencefinding0.746
Synthetic example showing an intervention that appears safe in tested contexts but causes behavior changes in others