arXiv (All)
open access
SHARD: Safe and Helpful Alignment via Self-Reframing Distillation
Large language models often struggle with sensitive prompts. They may refuse outright, provide generic safety boilerplate, or fail to address the user's legitimate informational needs that can be answered safely. We introduce SHARD, a self-reframing distillation method to improve safe-helpfulness. I
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
- SHARD: Safe and Helpful Alignment via Self-Reframing Distillation#920360
- Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives#1064302
- Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions#793331
- Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions#789327
- Pre-trained Language Models in Biomedical Domain: A Systematic Survey#421590
Record · ID 924592
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