arXiv (All)
open access
Rethinking GRPO for Large Reasoning Model Safety Alignment
Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely used for safety alignment, its group-relative optimization may provide insufficient safety-directed learning signals. In this paper,
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
- Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs#1389560
- SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment#632761
- The Alignment Tax: How Safety Training Creates Operationally Lethal AI Systems#248522
- TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards#997207
- SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems#1064893
Record · ID 1387373
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