arXiv (All)
open access
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models
Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introduces two axes that can influence safety alignment: when tokens are generated during denoising and where they appear in the response. In this paper, we
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
- $D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals#1143782
- Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models#1155197
- A Gravitational Interpretation of Safety Reversion under Fine-Tuning#1129317
- Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models#1123051
- State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking#1105126
Record · ID 819939
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