Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation

arXiv 2610.20652v1•0ffaebaa519673f74ffdde6ca4fbd287a0706d53f93f2486ae57b37784c338b3

Paper metadata

arXiv ID
2610.20652
Version
v1
Category
cs.CL
Authors
Vaibhav Prajapati, Pushp Garg
Publication date
2026-10-16T04:00:00Z
Source identifier
2610.20652v1
Public record ID
record:sha256:0ffaebaa519673f74ffdde6ca4fbd287a0706d53f93f2486ae57b37784c338b3

Source license ↗

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
0ffaebaa519673f74ffdde6ca4fbd287a0706d53f93f2486ae57b37784c338b3
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.

Record · Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation · Baitaphish