Transforming legal text into executable decision logic is a longstanding challenge in legal informatics. With the rise of LLMs, this task has gained renewed interest, but remains challenging due to requiring extensive manual coding and evaluation. We use a unique real-world dataset that pairs production-grade decision models with legal text from the Dutch Environment and Planning Act. These models power the Omgevingsloket government platform, where citizens check permit requirements for environmental activities. We study whether intermediate structured representations can improve LLM-based generation of executable decision models from legal text. We compare four input conditions: raw legal text, text enriched with semantic role labels, text enriched with input and output constraints, and text enriched with both. We evaluate along two dimensions: structural evaluation, through similarity to gold decision models with graph kernels and graphs' descriptive statistics, and outcome evaluation, through functional equivalence by executing models on pre-configured test scenarios. Our findings show that I/O constraints provide the dominant improvement (+37-54

Today's evolving labor markets rely increasingly on recommender systems for hiring, talent management, and workforce analytics, with natural language processing (NLP) capabilities at the core. Yet, research in this area remains highly fragmented. Studies employ divergent ontologies (ESCO, O*NET, national taxonomies), heterogeneous task formulations, and diverse model families, making cross-study comparison and reproducibility exceedingly difficult. General-purpose benchmarks lack coverage of work-specific tasks, and the inherent sensitivity of employment data further limits open evaluation. We present WorkRB (Work Research Benchmark), the first open-source, community-driven benchmark tailored to work-domain AI. WorkRB organizes 13 diverse tasks from 7 task groups as unified recommendation and NLP tasks, including job/skill recommendation, candidate recommendation, similar item recommendation, and skill extraction and normalization. WorkRB enables both monolingual and cross-lingual evaluation settings through dynamic loading of multilingual ontologies. Developed within a multi-stakeholder ecosystem of academia, industry, and public institutions, WorkRB has a modular design for seamless contributions and enables integration of proprietary tasks without disclosing sensitive data. WorkRB is available under the Apache 2.0 license at https://github.com/techwolf-ai/WorkRB.

The Second Search Futures Workshop, in conjunction with the Forty-seventh European Conference on Information Retrieval (ECIR) 2025, looked into the future of search to ask questions such as: • How can we navigate data privacy in large language model (LLM)-based information retrieval (IR)? • How can we implement agentic IR for proactive knowledge synthesis? • How do we ensure trustworthy information access beyond citations in the age of language models? • How does deep search transition from matching to reasoning? • What is meant by information semantics, knowledge representation, and natural language in a world of LLM-powered search? • What are serendipity engines, and how do they explore proactive web search via LLM agents, retrieval augmented generation (RAG), and simulated user feedback? The second edition of the workshop opened with ten lightning talks from a diverse group of speakers. Rather than traditional paper presentations, these short talks offered concise overviews of emerging ideas and critical insights, enabling a rapid exchange across various topics. The format was designed to spark discussion and expose participants to a broad spectrum of future-facing research directions in a compact timeframe. This report, co-authored by the workshop organizers, presenters, and participants, summarizes the talks and key discussions. Our aim is to share these insights with the broader IR community and help seed further dialogue around the themes raised. Date: 10 April 2025. Website: https://searchfutures.github.io/.

Understanding preferences, opinions, and sentiment of the workforce is paramount for effective employee lifecycle management. Open-ended survey responses serve as a valuable source of information. This paper proposes a machine learning approach for aspect-based sentiment analysis (ABSA) of Dutch open-ended responses in employee satisfaction surveys. Our approach aims to overcome the inherent noise and variability in these responses, enabling a comprehensive analysis of sentiments that can support employee lifecycle management. Through response clustering we identify six key aspects (salary, schedule, contact, communication, personal attention, agreements), which we validate by domain experts. We compile a dataset of 1,458 Dutch survey responses, revealing label imbalance in aspects and sentiments. We propose few-shot approaches for ABSA based on Dutch BERT models, and compare them against bag-of-words and zero-shot baselines. Our work significantly contributes to the field of ABSA by demonstrating the first successful application of Dutch pre-trained language models to aspect-based sentiment analysis in the domain of human resources (HR).

extended-abstract Share on Third Workshop on Recommender Systems for Human Resources (RecSys in HR 2023) Authors: Toine Bogers Department of Computer Science, IT University of Copenhagen, Denmark Department of Computer Science, IT University of Copenhagen, Denmark 0000-0003-0716-676XView Profile , David Graus Randstad, Netherlands Randstad, Netherlands 0000-0002-6245-0870View Profile , Mesut Kaya Department of Communication and Psychology, Aalborg University Copenhagen, Denmark Department of Communication and Psychology, Aalborg University Copenhagen, Denmark 0000-0003-2305-6683View Profile , Chris Johnson Indeed, USA Indeed, USA 0009-0007-5448-2833View Profile , Jens-Joris Decorte TechWolf, Belgium TechWolf, Belgium 0009-0000-7892-1211View Profile Authors Info & Claims RecSys '23: Proceedings of the 17th ACM Conference on Recommender SystemsSeptember 2023Pages 1244–1247https://doi.org/10.1145/3604915.3608755Published:14 September 2023Publication History 0citation70DownloadsMetricsTotal Citations0Total Downloads70Last 12 Months70Last 6 weeks70 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

This study explores the potential of reinforcement learning algorithms to enhance career planning processes. Leveraging data from Randstad The Netherlands, the study simulates the Dutch job market and develops strategies to optimize employees' long-term income. By formulating career planning as a Markov Decision Process (MDP) and utilizing machine learning algorithms such as Sarsa, Q-Learning, and A2C, we learn optimal policies that recommend career paths with high-income occupations and industries. The results demonstrate significant improvements in employees' income trajectories, with RL models, particularly Q-Learning and Sarsa, achieving an average increase of 5% compared to observed career paths. The study acknowledges limitations, including narrow job filtering, simplifications in the environment formulation, and assumptions regarding employment continuity and zero application costs. Future research can explore additional objectives beyond income optimization and address these limitations to further enhance career planning processes.

The increased digitization of the labour market has given researchers, educators, and companies the means to analyze and better understand the labour market. However, labour market resources, although available in high volumes, tend to be unstructured, and as such, research towards methodologies for the identification, linking, and extraction of entities becomes more and more important. Against the backdrop of this quest for better labour market representations, resource constraints and the unavailability of large-scale annotated data cause a reliance on human domain experts. We demonstrate the effectiveness of prompt-based tuning of pre-trained language models (PLM) in labour market specific applications. Our results indicate that cost-efficient methods such as PTR and instruction tuning without exemplars can significantly increase the performance of PLMs on downstream labour market applications without introducing additional model layers, manual annotations, and data augmentation.

Recommender Systems (RS) have proven successful in a wide variety of domains, and the human resources (HR) domain is no exception. RS proved valuable for recommending candidates for a position, although the ethical implications have recently been identified as high-risk by the European Commission. In this study, we apply RS to match candidates with job requests. The RS pipeline includes two fairness gates at two different steps: pre-processing (using GAN-based synthetic candidate generation) and post-processing (with greedily searched candidate re-ranking). While prior research studied fairness at pre- and post-processing steps separately, our approach combines them both in the same pipeline applicable to the HR domain. We show that the combination of gender-balanced synthetic training data with pair re-ranking increased fairness with satisfactory levels of ranking utility. Our findings show that using only the gender-balanced synthetic data for bias mitigation is fairer by a negligible margin when compared to using real data. However, when implemented together with the pair re-ranker, candidate recommendation fairness improved considerably, while maintaining a satisfactory utility score. In contrast, using only the pair re-ranker achieved a similar fairness level, but had a consistently lower utility.

Writing job vacancies can be a repetitive and expensive task for humans.This research focuses on automatically generating parts of vacancy texts, i.e., the benefits section, given structured job attributes as input using mT5, the multilingual version of the state-of-the-art T5 transformer model.While transformers are accurate at generating coherent text, they can struggle with correctly including structured (input) data in the generated text.Including this input data correctly is crucial for vacancy text generation; otherwise, job seekers may be misled.To evaluate how the model includes the different types of structured input, we propose a novel domain-specific metric: 'input generation accuracy'.Our metric aims to address the shortcomings of Relation Generation, a commonly used evaluation metric for data-to-text generation that relies on string matching, as our task includes evaluating generated texts based on binary and categorical inputs.Using our novel evaluation method, we measure how well the input is included in the generated text separately for different types of inputs (binary, categorical, numeric), offering another contribution to the field.In addition, we evaluate how accurately the mT5 model generates texts in the requested languages.Our experiments show that mT5 is highly accurate at generating texts in the correct (requested) languages, and at handling seen categorical and binary inputs correctly.However, mT5 performed worse when generating text from unseen city names or working with numeric inputs.

This research investigates the extent to which a reinforcement learning agent can learn the heuristics of a combinatorial optimisation problem (CO), personnel scheduling, from a graph representation. In recent years, reinforcement learning has emerged as an effective data-driven approach to solving CO problems, a subset of mathematical optimisation that appear in many real-world tasks and can be costly to solve in terms of computing power and/or human resource. CO problems often have an underlying graph structure with relational inductive biases that can be exploited by powerful graph neural networks. Acrossarangeofproblemcomplexities, ourapproachwasablereturnconsistentlyhighaveragereward, performing significantly better than baselines.

introduction Share on Second Workshop on Recommender Systems for Human Resources (RecSys in HR 2022) Authors: Toine Bogers Aalborg University Copenhagen, Denmark Aalborg University Copenhagen, DenmarkView Profile , David Graus Randstad Groep Nederland, Netherlands Randstad Groep Nederland, NetherlandsView Profile , Mesut Kaya Aalborg University Copenhagen, Denmark Aalborg University Copenhagen, DenmarkView Profile , Francisco Gutiérrez Computer Science, KU Leuven, Belgium Computer Science, KU Leuven, BelgiumView Profile , Sepideh Mesbah Randstad Groep Nederland, Netherlands Randstad Groep Nederland, NetherlandsView Profile , Chris Johnson Indeed, United States Indeed, United StatesView Profile Authors Info & Claims RecSys '22: Proceedings of the 16th ACM Conference on Recommender SystemsSeptember 2022Pages 671–674https://doi.org/10.1145/3523227.3547414Published:13 September 2022Publication History 0citation112DownloadsMetricsTotal Citations0Total Downloads112Last 12 Months42Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

In this paper we focus on constructing useful embeddings of textual information in vacancies and resumes, which we aim to incorporate as features into job to job seeker matching models alongside other features. We explain our task where noisy data from parsed resumes, heterogeneous nature of the different sources of data, and crosslinguality and multilinguality present domain-specific challenges. We address these challenges by fine-tuning a Siamese Sentence-BERT (SBERT) model, which we call conSultantBERT, using a large-scale, real-world, and high quality dataset of over 270,000 resume-vacancy pairs labeled by our staffing consultants. We show how our fine-tuned model significantly outperforms unsupervised and supervised baselines that rely on TF-IDF-weighted feature vectors and BERT embeddings. In addition, we find our model successfully matches cross-lingual and multilingual textual content.

In the era of big data, we continuously - and at times unknowingly - leave behind digital traces, by browsing, sharing, posting, liking, searching, watching, and listening to online content. When aggregated, these digital traces can provide powerful insights into the behavior, preferences, activities, and traits of people. While many have raised privacy concerns around the use of aggregated digital traces, it has undisputedly brought us many advances, from the search engines that learn from their users and enable our access to unforeseen amounts of data, knowledge, and information, to, e.g., the discovery of previously unknown adverse drug reactions from search engine logs. Whether in online services, journalism, digital forensics, law, or research, we increasingly set out to exploring large amounts of digital traces to discover new information. Consider for instance, the Enron scandal, Hillary Clinton's email controversy, or the Panama papers: cases that revolve around analyzing, searching, investigating, exploring, and turning upside down large amounts of digital traces to gain new insights, knowledge, and information. This discovery task is at its core about finding evidence of activity in the real world. This dissertation revolves around discovery in digital traces, and sits at the intersection of Information Retrieval, Natural Language Processing, and applied Machine Learning. We propose computational methods that aim to support the exploration and sense-making process of large collections of digital traces. We focus on textual traces, e.g., emails and social media streams, and address two aspects that are central to discovery in digital traces.

Recommender systems are increasingly used in more high risk application domains, including in the domain of Human Resources (HR). These recommender systems help end-users find relevant vacancies out of an abundant overload of available vacancies, but also support other important objectives such as job mobility. Despite the use in industry applications, there are several research challenges associated to such objectives that have not yet been addressed in detail in this context, such as supporting end-users to steer the recommendation process with input and feedback and increasing diversity of recommendations. The goal of our workshop is to build a strong research capacity around recommender systems for HR to address these challenges. This paper describes the goal and activities of the Workshop on Recommender Systems for Human Resources (RecSys in HR 2021), organized at the 15th ACM Conference on Recommender Systems. Date: 10--14 September, 2021. Website: https://foo2021.net.

1.1 Motivation The field of Human Resources (HR) is at the forefront of adopting AI technologies. According to PWC over 40% of HR-functions of international companies use AI-applications [4]. This so-called HR Technology (HR Tech) aims to replace or support Human Resource functions such as talent acquisition and management, employee compensation, workforce analytics, and performance management. Recommender Systems, broadly defined as systems that aim to support users in decision making by suggesting and offering relevant content, play an integral role in the rapid rise of HR Tech. Their applications range from assisting the talent acquisition process through matching [8], analyzing resumes or other user representations for candidate screening [20] and automated assessment [12, 14], to broader tasks such as recommendations for upskilling [19]. The use of AI applications in the recruitment process, such as recommender systems, is considered high-risk by the European Commission [21], as automation here can directly impact the (working) lives of people. In this light, the rise of AI-assisted hiring and

The labor market is constantly evolving. Occupations are changing, being added, or disappearing to fit the needs of today's market. In recent years the pace of this change has accelerated, due to factors such as globalization, digitization, and the shift to working from home. Different factors are relevant when selecting employment, e.g., cultural fit, compensation, provided degree of freedom. To successfully fulfill an occupation the gap between required (by the job) and possessed (by the job seeker) skills needs to be as small as possible. Decreasing this skill-gap improves the fit between a job candidate and occupation. In this paper we propose a custom-built Skills&Occupation Knowledge Graph (KG) that fits the above described dynamic nature of the labor market, by leveraging existing skills and occupation taxonomies enriched with external job posting data. We leverage this KG and explore several applications for skills-based matching of jobs to job seekers. First, we study link prediction as a means to quantify relevance of skills to occupations, which can help in prioritizing learning and development of employees. Next, we study node similarity methods and shortest path algorithms for career pathfinding. Finally, we leverage a term weighting method for identifying which skills are most"distinctive"for different (types of) occupations.

Audio features have been proven useful for increasing the performance of automated topic segmentation systems. This study explores the novel task of using audio embeddings for automated, topically coherent segmentation of radio shows. We created three different audio embedding generators using multi-class classification tasks on three datasets from different domains. We evaluate topic segmentation performance of the audio embeddings and compare it against a text-only baseline. We find that a set-up including audio embeddings generated through a non-speech sound event classification task significantly outperforms our text-only baseline by 32.3% in F1-measure. In addition, we find that different classification tasks yield audio embeddings that vary in segmentation performance.

With the uptake of algorithmic personalization in the news domain, news organizations increasingly trust automated systems with previously considered editorial responsibilities, e.g., prioritizing news to readers. In this paper we study an automated news recommender system in the context of a news organization's editorial values. We conduct and present two online studies with a news recommender system, which span one and a half months and involve over 1,200 users. In our first study we explore how our news recommender steers reading behavior in the context of editorial values such as serendipity, dynamism, diversity, and coverage. Next, we present an intervention study where we extend our news recommender to steer our readers to more dynamic reading behavior. We find that (i) our recommender system yields more diverse reading behavior and yields a higher coverage of articles compared to non-personalized editorial rankings, and (ii) we can successfully incorporate dynamism in our recommender system as a re-ranking method, effectively steering our readers to more dynamic articles without hurting our recommender system's accuracy.