Marc Palyart

Matthias De Lange, Warre Veys, Federico Retyk et al.

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 \textbf{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.

Warren Jouanneau, Aurélie Bugeau, Marc Palyart et al.

In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.

Warren Jouanneau, Marc Palyart, Emma Jouffroy

Finding the perfect match between a job proposal and a set of freelancers is not an easy task to perform at scale, especially in multiple languages. In this paper, we propose a novel neural retriever architecture that tackles this problem in a multilingual setting. Our method encodes project descriptions and freelancer profiles by leveraging pre-trained multilingual language models. The latter are used as backbone for a custom transformer architecture that aims to keep the structure of the profiles and project. This model is trained with a contrastive loss on historical data. Thanks to several experiments, we show that this approach effectively captures skill matching similarity and facilitates efficient matching, outperforming traditional methods.

Morgane Hoffmann, Emma Jouffroy, Warren Jouanneau et al.

General-purpose Large Language Models (LLMs) show significant potential in recruitment applications, where decisions require reasoning over unstructured text, balancing multiple criteria, and inferring fit and competence from indirect productivity signals. Yet, it is still uncertain how LLMs assign importance to each attribute and whether such assignments are in line with economic principles, recruiter preferences or broader societal norms. We propose a framework to evaluate an LLM's decision logic in recruitment, by drawing on established economic methodologies for analyzing human hiring behavior. We build synthetic datasets from real freelancer profiles and project descriptions from a major European online freelance marketplace and apply a full factorial design to estimate how a LLM weighs different match-relevant criteria when evaluating freelancer-project fit. We identify which attributes the LLM prioritizes and analyze how these weights vary across project contexts and demographic subgroups. Finally, we explain how a comparable experimental setup could be implemented with human recruiters to assess alignment between model and human decisions. Our findings reveal that the LLM weighs core productivity signals, such as skills and experience, but interprets certain features beyond their explicit matching value. While showing minimal average discrimination against minority groups, intersectional effects reveal that productivity signals carry different weights between demographic groups.

Warren Jouanneau, Emma Jouffroy, Marc Palyart

Finding the most relevant person for a job proposal in real time is challenging, especially when resumes are long, structured, and multilingual. In this paper, we propose a re-ranking model based on a new generation of late cross-attention architecture, that decomposes both resumes and project briefs to efficiently handle long-context inputs with minimal computational overhead. To mitigate historical data biases, we use a generative large language model (LLM) as a teacher, generating fine-grained, semantically grounded supervision. This signal is distilled into our student model via an enriched distillation loss function. The resulting model produces skill-fit scores that enable consistent and interpretable person-job matching. Experiments on relevance, ranking, and calibration metrics demonstrate that our approach outperforms state-of-the-art baselines.

Cédric Teyton, Jean-Rémy Falleri, Marc Palyart et al.

Software intensively depends on external libraries whose relevance may change during its life cycle. As a consequence, software developers must periodically reconsider the libraries they depend on, and must think about \textit{library migration}. To our knowledge, no existing study has been done to understand library migration although it is known to be an expensive maintenance task. Are library migrations frequent? For which software are they performed and when? For which libraries? For what reasons? The purpose of this paper is to answer these questions with the intent to help software developers that have to replace their libraries. To that extent, we have performed a statistical analysis of a large set of open source software to mine their library migration. To perform this analysis we have defined an approach that identifies library migrations in a pseudo-automatic fashion by analyzing the source code of the software. We have implemented this approach for the Java programming language and applied it on Java Open Source Software stored in large hosting services. The main result of our study is that library migration is not a frequent practice but depends a lot on the nature of the software as well as the nature of the libraries.

Jean-Rémy Falleri, Cédric Teyton, Matthieu Foucault et al.

According to Wikipedia, The Mining Software Repositories (MSR) field analyzes the rich data available in software repositories, such as version control repositories, mailing list archives, bug tracking systems, issue tracking systems, etc. to uncover interesting and actionable information about software systems, projects and software engineering. The MSR field has received a great deal of attention and has now its own research conference : http://www.msrconf.org/. However performing MSR studies is still a technical challenge. Indeed, data sources (such as version control system or bug tracking systems) are highly heterogeneous. Moreover performing a study on a lot of data sources is very expensive in terms of execution time. Surprisingly, there are not so many tools able to help researchers in their MSR quests. This is why we created the Harmony platform, as a mean to assist researchers in performing MSR studies.