Recoverability-Controlled Safety Miscalibration in Large Language Models
arXiv 2610.22425v1•dd2238747e1e6da5c00e4a33a5c92890116fa3ef3f52037d13ee23198c75c517
Paper metadata
- arXiv ID
- 2610.22425
- Version
- v1
- Category
- cs.AI, cs.CR
- Authors
- Yuwei Wang, Xingwang Liang, Yu Xie, Haotian Chi, Haijun Geng
- Publication date
- 2026-10-19T04:00:00Z
- Source identifier
- 2610.22425v1
- Public record ID
- record:sha256:dd2238747e1e6da5c00e4a33a5c92890116fa3ef3f52037d13ee23198c75c517
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- dd2238747e1e6da5c00e4a33a5c92890116fa3ef3f52037d13ee23198c75c517
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.