Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione
arXiv 2609.25049v1•8bad572830e108c9654b67a895b103f7f2cfeef978ae3ea56fa3956fa6aaeea9
Paper metadata
- arXiv ID
- 2609.25049
- Version
- v1
- Category
- cs.AI, cs.CL
- Authors
- Zixuan Wang, Bingjie Zhang, He Zhao, Dandan Guo
- Publication date
- 2026-09-23T04:00:00Z
- Source identifier
- 2609.25049v1
- Public record ID
- record:sha256:8bad572830e108c9654b67a895b103f7f2cfeef978ae3ea56fa3956fa6aaeea9
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
- 8bad572830e108c9654b67a895b103f7f2cfeef978ae3ea56fa3956fa6aaeea9
- 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.