arXiv (All)
open access
Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering
Instruct-TTS systems expand structured style labels into natural-language training instructions through LLM rewriting, yet we find that over 40% of unconstrained rewrites contain semantic drift that corrupts supervision and weakens generalization. We formalize this problem as instruction supervision
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
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example#927037
- Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets#986202
- Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning#799861
- 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation#1050609
- Inductive Feedback for Mixed-Policy Distillation#1129980
Record · ID 985579
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