arXiv (All)
open access
Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning
LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to three structural problems: conflicting gradients that cancel, static data selection that cannot track evolving learning dynamics, and subspace saturation
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Specializing Without Forgetting: Analyzing Knowledge Preservation in Multilingual Model Adaptation#1186477
- When do data mixtures improve scaling laws? Insights from high-dimensional regression#1142312
- When do data mixtures improve scaling laws? Insights from high-dimensional regression#1122304
- OptiSelect: How does the Optimizer Shape Data Curriculum?#1188110
- OptiSelect: How does the Optimizer Shape Data Curriculum?#1181662
Record · ID 1216928
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive