Fragility, the activation noise level causing probe accuracy collapse, reveals evolving lexical-to-compositional moral encoding, layer robustness gradients, and fine-tuning differences invisible to saturated probing accuracy.
Towards tracing trustworthiness dy- namics: Revisiting pre-training period of large language models.arXiv preprint arXiv:2402.19465
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Benign fine-tuning drifts LLM parameters toward danger directions; SQSD scores each sample by the projection difference of its induced update onto safety versus danger vectors.
citing papers explorer
-
When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis
Fragility, the activation noise level causing probe accuracy collapse, reveals evolving lexical-to-compositional moral encoding, layer robustness gradients, and fine-tuning differences invisible to saturated probing accuracy.
-
From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
Benign fine-tuning drifts LLM parameters toward danger directions; SQSD scores each sample by the projection difference of its induced update onto safety versus danger vectors.