arXiv (All)
open access
DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution
Data selection for instruction tuning is usually studied for efficiency, reaching strong performance with a fraction of the training data. We ask whether data selection can instead raise the performance ceiling, producing a better model than training on all the available data. To test this, we take
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
- An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models#2681
- On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training#1131860
- Noisy Test-Time Reinforcement Learning for Code LLMs#1116503
- When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair#303019
- Relaxed SEM-Based Out-of-Sample Predictions#637590
Record · ID 1116340
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