arXiv (All)
open access
PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy Distillation (OPD) can improve teacher-guided adaptation by supervising student-generated rollouts, while GRPO-bas
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
- Trapped by Their Own Rollouts: Understanding Aggregation--Rollout Feedback in Federated On-Policy Distillation#1116904
- WASD: Wasserstein-based Knowledge Distillation for Large Language Models#1217081
- Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall#821565
- LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure#1048729
- Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?#1118864
Record · ID 1248094
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