H2DF: Calibrated Target Bands for Controllable Language-Model Unlearning
arXiv 2610.26864v1•ce3950a5f0a7397d63368a1cb8c674f3fdf68583a79fed1a0fc5ec57f8a1fc4c
Paper metadata
- arXiv ID
- 2610.26864
- Version
- v1
- Category
- cs.CL, cs.LG
- Authors
- Jupiter Yao
- Publication date
- 2026-10-21T04:00:00Z
- Source identifier
- 2610.26864v1
- Public record ID
- record:sha256:ce3950a5f0a7397d63368a1cb8c674f3fdf68583a79fed1a0fc5ec57f8a1fc4c
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
- ce3950a5f0a7397d63368a1cb8c674f3fdf68583a79fed1a0fc5ec57f8a1fc4c
- 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.