cs.CLNov 17, 2026

Prioritize, Don't Decide: What We Learned Auditing a Deployed Human-in-the-Loop CV Sorter

Authors: Hadi Mohammadi, Jeroen Sparla, Alexandros Paliouras, Georg Krempl, Robert A. Bagheri

Organizations: AcademicTransfer, Utrecht, The Netherlands · Department of Methodology, Statistics & Data Science, Utrecht University, The Netherlands · Department of Information and Computing Sciences, Utrecht University, The Netherlands

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.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 2, 2026

CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening

Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability model to every candidate and criterion is costly. We present CreateScore, a domain-theory-informed Bayesian network for criterion-level LLM routing. A hand-specified directed acyclic graph with Dirichlet-multinomial conditional probability tables converts CV evidence into posterior uncertainty; low-uncertainty decisions are resolved by a local 8B model and uncertain ones are escalated to a 120B reference model. The graph is causally motivated, but the system performs standard Bayesian conditioning, not causal inference. The escalation threshold is calibrated on a training fold (target: 70% resolved locally) and then frozen. On 200 synthetic Data Science CVs (139 training and 61 test candidates, five criteria), 77.7% of criterion decisions were resolved locally (237 of 305). Relative to a reference condition in which the 120B model adjudicated every criterion, routed escalation reduced token use by 65.2% and raised exact score agreement from 32.8% (8B alone) to 42.6% (95% CI 31.0-55.1%); at n = 61 the gain was not statistically distinguishable. The uncertainty signal did not, however, identify the decisions on which the 8B model erred: disagreement with the reference was 16.2% among escalated and 19.4% among locally resolved decisions (AUROC 0.47, 95% CI 0.39-0.56), no better than random selection. We also document how an earlier evaluation was invalidated when truncated reasoning-model outputs were silently replaced by local labels, and we recommend safeguards for cascade evaluation. CreateScore is supported as an auditable cost-reduction mechanism, not yet as a targeted error detector, and is not an autonomous hiring system.
Jun 14, 2026

Surprise-Guided MergeSort: Budget-Efficient Human-in-the-Loop Ranking via Adaptive Comparison Scheduling

Pairwise comparison is the gold standard for subjective ranking tasks; however, exhaustive annotation requires a massive number of human comparisons (O(n2)O(n^2)). While sorting-based methods have reduced this burden to O(nlog⁡n)O(n\log n), they still require expensive human judgment for every single comparison. To further improve annotation efficiency, we propose leveraging a Vision-Language Model (VLM) not as an annotator replacement, but as a question prioritizer to identify which comparisons genuinely require human judgment. The proposed Surprise-Guided MergeSort (SGS) framework achieves this through three integrated components: (1) a bottom-up MergeSort scheduler that structures comparisons and exploits transitivity, (2) a composite Surprise Scorer -- combining position-bias-cancelled VLM confidence, Elo gap, and vote entropy -- to quantify comparison ambiguity, and (3) an adaptive budget allocator that routes high-surprise pairs to humans while automating low-surprise pairs via transitivity inference. Validation was conducted on six diverse benchmarks spanning text similarity (STS-B, BIOSSES, SICKR-STS) and image quality assessment (KonIQ-10k, TID2013, LIVE Challenge). SGS effectively identified and skipped up to 535 non-informative comparisons per session. Consequently, it achieved Kendall's τ×100τ{\times}100 improvements of +6+6 to +12+12 over Active Elo under the same total budget. These results demonstrate that combining VLM-guided surprise metrics with algorithmic sorting provides a generally consistent accuracy-efficiency trade-off across diverse domains.
Oct 30, 2026

AI evaluators favor job applications written by certain AI models, independent of candidate quality

Job applicants increasingly use large language models (LLMs) to write cover letters, while employers deploy LLMs to screen them. In this all-AI setting, we ask whether the choice of model affects hiring outcomes independently of candidate qualifications. We introduce a multi-model auditing framework pairing eleven LLM writer agents with nine API-hosted evaluator agents across ten job descriptions and fifty candidates per job. Four findings emerge. First, we identify a generative preference hierarchy: a consistent global ranking of writer models by evaluator acceptance, in which locally hosted models are systematically disadvantaged regardless of their license, compounded by self-preference bias where evaluators favour their own outputs. Second, evaluator models differ substantially in how much bias they introduce based on applicants' tool choice, offering actionable guidance for fairer screening design. Third, this hierarchy has measurable competitive consequences: in the most adverse pairing, approximately two (1.8) out of twenty-five qualified candidates are filtered out purely due to model mismatch. Fourth, a common mechanism explains the patterns above: writer preference and self-preference trace to a combination of how much each writer leans on specific stylistic cues and how strongly evaluators, often unanimously, reward or penalise those same cues. A further check finds little evidence that an unmeasured "writer fingerprint" remains once these same features are accounted for. We discuss implications for algorithmic fairness in employment, regulation of AI-assisted screening, and the design of auditing frameworks that can be reapplied as the model landscape evolves.