AI & ML
Prioritize, Don't Decide: What We Learned Auditing a Deployed Human-in-the-Loop CV Sorter
arXiv cs.IR0 views
arXiv:2611.23359v1 Announce Type: cross Abstract: A single academic vacancy can draw hundreds of applications, and the first screening round consumes most of a committee's time. We describe a CV Priority Sorter deployed at a national platform for academic vacancies and integrated with its vacancy database. It proposes a reading order for a pile of CVs and leaves every decision to the committee, pairing a frozen multilingual transformer encoder with a per-session linear model that retrains after each label and is discarded when the session ends. It works: on a pool of 300 synthetic CVs, a committee reading in the tool's order reaches 95% of the relevant candidates after half the pile, where an arbitrary order needs almost all of it. This paper is about what we found when we audited that claim, rather than about the system itself. Three findings changed the product. The pool turned out to be sortable by document length alone, which makes precision-style metrics on it uninformative; regenerating it under a shared length budget removes that shortcut and leaves the reading-depth result standing. The four-level agreement score such systems report, ours included, is a binary probability cut at fixed thresholds, so it follows the classifier's confidence rather than its ranking and falls as labels accumulate. And uncertainty sampling, the obvious way to implement a "suggest the next CV" button, leaves model quality intact but raises the committee's total reading load above the no-label baseline, because the CVs it asks about are the ones that would otherwise be skipped. A fourth result shows where to look next: a hosted LLM embedding model lifts zero-label ordinal discrimination from 0.66 to 0.80 under length control, then stops mattering once the session model has two dozen labels; a local cross-encoder matches that cold-start gain without sending data out. We report the fixes each finding forced.
Source:https://arxiv.org/abs/2611.23359PreviousCan Programs Replace LLM Judges? Executable Program Judges for Scalable and Efficient Relevance LabelingNextLusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese
Related posts
Our health check said "db ok" for 40 minutes. It was talking to a cache.
0dev.to WebDev
Banco do Brasil: acesso indevido pode ter exposto CPF, e-mail e dados bancários
0dev.to Security

When the Attacker Has No Return Address
0dev.to Security
La nube te mantiene responsable de todos modos; lo local simplemente nunca comet
0dev.to Security
Interrupções em bancos e redes da NSA são ligadas a correções de falhas por IA
0dev.to Security
Reverse Path Filtering Is Not a Substitute for Routing Policy
0dev.to Linux