arXiv (All)
open access
Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione
Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions. Prior studies primarily attribute this to static representation overlap, largely overlooking the underlying dynamic mechanisms. In this paper, we present the
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
- Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning#1154943
- PRISM: Recovering Instruction Sets from Language Model Activations#1117460
- A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs#927819
- Combating Instruction Conflict via Energy-Driven Latent Conflict Detection#985980
- Self-reported archetypes and behavioral failures in Large Language Models#1110396
Record · ID 1051542
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