A new phone-secretary benchmark shows quality scaling with capability, no triage scaling once degenerate baselines are subtracted, and more capable models relaying scam callback numbers more often.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CallScreenBench: Benchmarking On-Device Models as Phone Secretaries
A new phone-secretary benchmark shows quality scaling with capability, no triage scaling once degenerate baselines are subtracted, and more capable models relaying scam callback numbers more often.