expert recruitment

Contemporary technical hiring practices suffer from stress-induced bias and evidentiary gaps, resulting in distorted competency assessments and compromised fairness. Method: This paper proposes an evidence-driven paradigm for software engineer competency evaluation. It systematically identifies and bridges evidentiary gaps in technical hiring through (1) multi-source behavioral data integration, (2) low-stress, authentic task design, and (3) a verifiable fairness framework grounded in educational measurement, human-computer interaction evaluation, algorithmic fairness auditing, and structured competency modeling. Contribution/Results: The approach yields a scalable, empirically validated hiring effectiveness metric suite. Empirical evaluation demonstrates significant improvements in employer hiring accuracy. Crucially, it establishes a reproducible, auditable foundation for equitable assessment—enhancing both validity and procedural fairness for candidates while enabling rigorous, transparent evaluation of hiring systems.

To address low matching accuracy and inefficiency in multi-position concurrent recruitment, this paper proposes an end-to-end intelligent recommendation method that integrates large language model (LLM)-driven semantic understanding with graph-structured similarity computation. We innovatively construct a dual-perspective, multimodal embedding representation—jointly modeling candidates and positions—to unify resumes and job descriptions into a shared semantic space; further, we employ graph neural networks to capture cross-entity relational dependencies, enabling dynamic and interpretable multi-vacancy collaborative matching. Our approach is the first to deeply fuse LLM-powered fine-grained semantic parsing with graph-structural similarity measurement. Evaluated on a real-world recruitment dataset, it achieves an average 32.7% improvement in matching precision and recall, while reducing initial screening time by over 60%.

Communication barriers between data scientists and domain experts arise from oversimplified, accuracy-centric model performance reporting, hindering shared understanding of model limitations and contextual applicability. Method: We propose a visualization-mediated model explanation framework grounded in human-computer interaction principles, participatory design, and visual narrative techniques. This yields the first domain-expert-oriented model communication guideline—emphasizing risk, trade-offs, and situational appropriateness rather than isolated metrics like accuracy. An iterative empirical study was conducted using regression models, incorporating structured expert feedback for evaluation. Contribution/Results: The framework significantly improves domain experts’ ability to identify model limitations, recognize inherent trade-offs, and proactively make context-driven adoption decisions. Its core innovation lies in repositioning visualization as an interdisciplinary consensus-building medium—shifting the paradigm from “metric reporting” to “collaborative understanding.”

This paper addresses systemic unfairness in AI-driven recruitment—manifesting as ranking bias and inaccurate interview evaluations—stemming from the propagation of human biases. It proposes the first end-to-end fairness analysis framework for recruitment AI. Methodologically, it explicitly disentangles bias sources across data, algorithm, and deployment layers, integrating a socio-technical systems perspective with statistical fairness metrics (Demographic Parity, Equalized Odds), three categories of bias mitigation strategies, and a third-party audit toolchain. Key contributions include: (1) taxonomizing 12 canonical bias scenarios; (2) constructing a fairness evaluation matrix comprising 27 operational metrics; and (3) proposing organization-aware, co-optimization pathways balancing fairness and operational efficacy. The work establishes a theoretical analytical paradigm for academia and delivers an actionable governance roadmap for industry, bridging critical gaps in cross-layer bias attribution and real-world impact assessment.

This study addresses the unclear ways in which large language models (LLMs) weigh candidate attributes, align with human preferences, and potentially exhibit implicit biases in hiring decisions. Introducing, for the first time, a full-factorial experimental design from economics—commonly used to analyze human hiring behavior—into LLM research, the authors construct a synthetic dataset based on real freelancing profiles to systematically evaluate how models implicitly assign weights to matching criteria such as skills and experience. The analysis further examines fairness across different project contexts and demographic groups. Findings indicate that LLMs primarily rely on core productivity signals and show no significant group-level discrimination overall; however, the weight assigned to these signals varies across intersecting demographic subgroups, revealing latent implicit biases in specific subgroup interactions.

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them costly and prone to randomness, ambiguity, and limited reproducibility. This study proposes a new competency modeling process built on large language models (LLMs). Instead of merely automating isolated steps, we reconstruct the workflow by decomposing expert practices into structured computational components. Specifically, we leverage LLMs to extract behavioral and psychological descriptions from raw textual data and map them to predefined competency libraries through embedding-based similarity. We further introduce a learnable parameter that adaptively integrates different information sources, enabling the model to determine the relative importance of behavioral and psychological signals. To address the long-standing challenge of validation, we develop an offline evaluation procedure that allows systematic model selection without requiring additional large-scale data collection. Empirical results from a real-world implementation in a software outsourcing company demonstrate strong predictive validity, cross-library consistency, and structural robustness. Overall, our framework transforms competency modeling from a largely qualitative and expert-dependent practice into a transparent, data-driven, and evaluable analytical process.

This study investigates hiring professionals’ misperceptions of their decision-making autonomy when using generative artificial intelligence (genAI), revealing how genAI acts as a “stealth architect” that subtly reshapes the informational foundations and evaluation criteria of recruitment processes. Through semi-structured interviews and thematic analysis with 22 hiring practitioners, the research finds that despite participants’ belief in retaining ultimate decision authority, their judgments are significantly shaped by the AI system. Although genAI offers modest efficiency gains, it concurrently contributes to the erosion of professional expertise and diminishes human capacity to oversee high-stakes decisions. The findings highlight the latent risks of human-AI collaboration under institutional pressures to adopt emerging technologies, offering critical insights for the design of responsible AI systems in hiring contexts.

Existing approaches struggle to evaluate the effectiveness and fairness of large language models (LLMs) in resume screening when ground-truth ranking labels are unavailable and potential biases are present. This work proposes the first annotation-free auditing framework, which constructs a set of comparable synthetic resumes with known relative qualifications to systematically assess the ranking performance of mainstream LLMs. The study reveals that most models fail to consistently identify more qualified candidates and lack a principled abstention mechanism when candidates are equally qualified. Furthermore, these models exhibit inconsistent selection rates across demographic groups, occasionally displaying unexpected preferences for historically marginalized populations. This research establishes a reproducible evaluation paradigm for assessing the reliability and fairness of LLMs in high-stakes hiring scenarios.

This study addresses severe congestion in the interview stage of academic statistics faculty hiring, which obscures candidates’ true preferences and leads to mismatches and unfilled positions. The authors model interview assignment as a statistical ranking problem under uncertainty, innovatively integrating market design with statistical learning. Candidates report their preferences over job attributes via a standardized questionnaire, while departments estimate offer probabilities and expected utilities using application materials and historical data. A confidence-calibrated pairwise utility ranking mechanism is then employed to select interviewees. This mechanism provides statistical guarantees, incentivizes truthful preference revelation, and enhances matching stability. Empirical evaluation using data from U.S. statistics departments demonstrates that the proposed framework substantially improves both match rates and quality while significantly reducing hiring failure rates.

This work addresses the challenge of accurately matching papers to reviewers in large-scale academic peer review, where existing approaches are limited by coarse similarity metrics or non-scalable manual annotations. The authors propose MERIT, a two-stage framework that first leverages large language models (LLMs) to generate reward signals based on fine-grained rubric-guided expertise criteria, then trains a 4B-parameter reviewer evaluator via reinforcement learning. In the second stage, the knowledge of this evaluator is distilled into an efficient embedding-based retriever to enable scalable reviewer assignment. This study is the first to formulate granular expertise matching as a supervised signal, achieving state-of-the-art performance on the LR-Bench and CMU Gold datasets. Notably, the specialized evaluator outperforms larger general-purpose LLMs on reviewer-paper fit classification tasks.