Latest articles
Nihed Bendahman Ph.D. thesis defense: “Evaluation and mitigation of hallucinations in automatic summarization in the specific context of legal documents”
Monday 15th December at 2p.m. Paris time, Nihed Bendahman, Ph.D. Candidate has defended her thesis named “Evaluation and mitigation of hallucinations in automatic summarization in the specific context of legal documents”. Her thesis defense took place at the IRIT Research Laboratory, in Toulouse, France. Take a look at the summary below. Summary Legal monitoring is a particularly time-consuming activity: to keep up with a constantly evolving law, experts must read dozens
Automatic Merge Request reviewer with AutoCodeReview
Article co-authored by : Kilian Bauvent (Lead engineer), Benoit Verhaeghe (Project manager and Techn Lead), Marius Pingaud (Developer on BL.CodeRules and diagram designer), Nicolas Hlad (Blog post author and survey designer) On the importance of Merge Requests The overall Merge request Process at Berge-Levrault Let us start by giving the big picture. At Berger-Levrault, developers
Experimenting with Innovation in Real-Life Situations: the Key to User-Centered Co-Design
Key words: Innovation – Living Lab – User-centered co-design – Real-life situation – Human and Social Science – Safety – Market launch Innovation at the heart of Berger-Levrault’s strategy A long tradition Innovation is not simply the emergence of new ideas, but their effective implementation to meet the challenges of an ever-changing world. At Berger-Levrault,
Automatic Evaluation of LLM and RAG: Foundations and Established Methods
In professional environments, an increasing number of companies are integrating Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) solutions to automate specific tasks or support their teams. However, ensuring the accuracy and relevance of these systems’ responses is critical, particularly when handling sensitive data or high-stakes business decisions. Evaluating these models requires a rigorous approach,
From the Iberian sun to the Rising sun for federated learning
On September 2024, we had the opportunity to attend two international conferences related to a segment of our work in artificial intelligence : Data Training Without Perturbative Adjustments for Predictive Maintenance The FLTA24 took place from September 17 to 19 in Valencia, Spain. As part of this research, we studied a concrete case: predictive maintenance,
Discover our 2024 Research & Innovation Yearbook!
We are delighted to present the first edition of the Research and Innovation Yearbook. This annual retrospective reflects the commitment and ambition of our Research and Technological Innovation Department at Berger-Levrault (also available in French and Spanish versions below). By highlighting our most audacious projects and innovative initiatives, we hope to share with you the
You can not avoid it! — measuring the energy consumption of software systems has become essential
Measuring the consumption of software systems is becoming increasingly important for industries. Software systems accounted for 6% of the world’s energy in 2019, surpassing civil aviation for gas emissions. Governments and European administrations must consider software energy consumption when selecting products to reduce the ecological impact. Thus, it becomes essential to measure the energy consumption
WeMagnus intelligent assistant: digital innovation for City Hall General Secretaries
As a management platform dedicated to local authorities, Berger-Levrault’s WeMagnus software stands out for solutions based on the latest advances in artificial intelligence (AI) and automated information processing. This new Intelligent Assistant offers users precise, contextualized support. But how was this tool designed? What technologies does it embody? What are its specific features? Designed as
Julien at EKAW 2024 for his work on extracting legal data from LLMs
On December 3, 2024 in Amsterdam, Julien Breton – Research Engineer at Berger-Levrault (Team BL.Research) took part in the EKAW 2024 (European Knowledge Acquisition Workshop) conference. His paper demonstrates how the alliance between large language models (LLMs) and software architectures can optimize data annotation: a consequent time and cost saving, and greater reliability for technical
Benoit receives the Prix Science Ouverte 2024: Recognition of excellence and openness in Research at Berger-Levrault
In a world where science plays a crucial role in meeting economic, environmental and societal challenges, the notion of openness in research is taking on strategic importance. Organised by the Committee for Open Science (CoSO) and supported by the French Ministry of Higher Education and Research, the Open Science Awards embody this commitment by recognising
Automate the discovery of anomalous behaviour with unsupervised anomaly detection
Unsupervised anomaly detection makes it possible to automate tasks relating to the maintenance of equipment and infrastructure, which until now have been carried out by experts. One of the features of the BL.Predict equipment management platform is the ability to manually define alert thresholds so that you are warned when the systems being monitored break
Forum for advances in visualization and visual analytics – VIS 2025 (Vienna – Austria)
IFIP/SOCOLNET – Hybrid Human-AI Collaborative Networks (Porto – Portugal)
La Mêlée Numérique – Artificial Revolutions (Toulouse – France)
Nihed Bendahman Ph.D. thesis defense: “Evaluation and mitigation of hallucinations in automatic summarization in the specific context of legal documents”
Monday 15th December at 2p.m. Paris time, Nihed Bendahman, Ph.D. Candidate has defended her thesis named “Evaluation and mitigation of hallucinations in automatic summarization in the specific context of legal documents”. Her thesis defense took place at the IRIT Research Laboratory, in Toulouse, France. Take a look at the summary below. Summary Legal monitoring is a
Gabriel Darbord Ph.D. thesis defense: “Automatic test generation to help modernize our applications”
Friday 5th December at 9a.m. Paris time, Gabriel Darbord, Ph.D. Candidate has defended his thesis named “Automatic test generation to help modernize our applications”. His thesis defense took place in Lille, France. Take a look at the summary below. This thesis is fully in line with the partnership between Berger-Levrault and Inria, which aims to
Berger-Levrault strengthens its ties with AI startups!
We are proud to announce that we have joined Hub France IA, the largest association dedicated to artificial intelligence in France. This network now brings together more than 250 members—companies, startups, research laboratories, and institutions—who share the same goal: to accelerate the development and adoption of AI in France and Europe. Getting closer to the
Celebrating New PhDs from the BL.Research Team!
At Berger-Levrault, research is more than a mission—it’s a shared adventure. As the new academic year begins, we are proud to celebrate the success of four of our colleagues from the BL.Research team, who have reached a major milestone in their scientific journeys: the defense of their doctoral theses. These achievements are the result of
Hamza Safri Ph.D. thesis defense: “Federated learning for the IoT : Application for Industry 4.0”
Thuesday 24th June at 3pm Paris time, Hamza Safri, Ph.D. Candidate has defended his thesis named “Federated learning for the IoT: Application for Industry 4.0”. His thesis defense took place at the Inria Minatec Grenoble, Grenoble, France. Take a look at the summary below. Keywords: Model generalization, predictive maintenance, industrial IoT, federated learning, edge network,
ESUG 2025: Six contributions and 2 prizes for the Software Engineering Lab team!
Congratulations to our PhDs Nicolas Hlad, Aless Hosry, Benoit Verhaeghe and Pascal Zaragoza from Berger-Levrault’s BL.Research team for their participation in the 2025 edition of the ESUG (European Smalltalk User Group) conference! This year’s conference took place from July 1-4 in Gdansk, Poland. The theme was innovation in Smalltalk technologies and their use in software
Julien Breton Ph.D. thesis defense: “Extraction and formalization of regulatory industrial maintenance knowledge from semi-structured corpus data”
Friday, 27th June at 1.30 pm Paris time, Julien Breton, Ph.D. Candidate has defended his thesis named “Extraction and formalization of regulatory industrial maintenance knowledge from semi-structured corpus data”. His thesis defense took place at the IRIT research laboratory, Toulouse, France. Take a look at the summary below. Keywords: Legal compliance,Industrial maintenance, Norm extraction,LLM (Large
New White Paper – AI for maintenance! Challenges, Opportunities and Case Studies
How is artificial intelligence transforming maintenance practices today? What are the concrete opportunities for equipment, infrastructure and fleet managers? The new white paper published by CARL Berger-Levrault offers a rich and accessible insight into these strategic questions. Entitled “AI at the service of maintenance: challenges, opportunities and case studies”, this document summarizes experience in the
