Using the example of the film 2001: A Space Odyssey, this chapter illustrates the challenges posed by an AI capable of making decisions that go against human interests. But are human decisions always rational and ethical? In reality, the cognitive decision-making process is influenced by cognitive biases that affect our behavior and choices. AI not only reproduces these biases, but can also exploit them, with the potential to shape our decisions and judgments. Behind IA algorithms, there are sometimes individuals who show little concern for fundamental rights and impose their own rules. To address the ethical and societal challenges raised by AI and its governance, the regulation of digital platforms and education are keys levers. Regulation must reflect ethical, legal, and political choices, while education must strengthen digital literacy and teach people to make informed and critical choices when facing digital technologies.

Many words are ambiguous in terms of their part of speech (POS). However, when a word appears in a text, this ambiguity is generally much reduced. Disambiguating POS involves using context to reduce the number of POS associated with words, and is one of the main challenges of lexical tagging. The problem of labeling words by POS frequently arises in natural language processing, for example for spelling correction, grammar or style checking, expression recognition, text-to-speech conversion, text corpus analysis, etc. Lexical tagging systems are thus useful as an initial component of many natural language processing systems. A number of recent lexical tagging systems produce multiple solutions when the text is lexically ambiguous or the uniquely correct solution cannot be found. These contributions aim to guarantee a zero silence rate: the correct tag(s) for a word must never be discarded. This objective is unrealistic for systems that tag each word uniquely. This article concerns a lexical disambiguation method adapted to the objective of a zero silence rate and implemented in Silberztein's INTEX system (1993). We present here a formal description of this method. We show that to verify a local disambiguation grammar in this framework, it is not sufficient to consider the transducer paths separately: one needs to verify their interactions. Similarly, if a combination of multiple transducers is used, the result cannot be predicted by considering them in isolation. Furthermore, when examining the initial labeling of a text as produced by INTEX, ideas for disambiguation rules come spontaneously, but grammatical intuitions may turn out to be inaccurate, often due to an unforeseen construction or ambiguity. If a zero silence rate is targeted, local grammars must be carefully tested. This is where a detailed specification of what a grammar will do once applied to texts would be necessary.

This work presents our participation in the EvalLLM 2025 challenge on biomedical Named Entity Recognition (NER) and health event extraction in French (few-shot setting). For NER, we propose three approaches combining large language models (LLMs), annotation guidelines, synthetic data, and post-processing: (1) in-context learning (ICL) with GPT-4.1, incorporating automatic selection of 10 examples and a summary of the annotation guidelines into the prompt, (2) the universal NER system GLiNER, fine-tuned on a synthetic corpus and then verified by an LLM in post-processing, and (3) the open LLM LLaMA-3.1-8B-Instruct, fine-tuned on the same synthetic corpus. Event extraction uses the same ICL strategy with GPT-4.1, reusing the guideline summary in the prompt. Results show GPT-4.1 leads with a macro-F1 of 61.53% for NER and 15.02% for event extraction, highlighting the importance of well-crafted prompting to maximize performance in very low-resource scenarios.

Animating a Knowledge Base: From Ontologies to Generative AI Models From Expert Systems and the Semantic W eb to Generative AI: Model - Driven and Data - Driven Approaches in Area Studies In a context where the social sciences and humanities are experimenting with non - anthropocentric analytical frames, this article proposes a semiotic (structural) reading of the hybridization between symbolic AI and neural (or sub - symbolic) AI based on a field of application: the design and use of a knowledge base for area studies. W e describe the LaCAS ecosystem - Open Archives in Linguistic and Cultural Studies (thesaurus; RDF/OWL ontology; LOD services; harvesting; expertise; publication), deployed at Inalco (National Institute for Oriental Languages and Civilizations) in Paris with the Okapi (Open Knowledge and Annotation Interface) software environment from Ina (National Audiovisual Institute), which now has around 160,000 documentary r esources and ten knowledge macro - domains grouping together several thousand knowledge objects. W e illustrate this approach using the knowledge domain "Languages of the world" (~540 languages) and the knowledge object "Quechua (language)". On this basis, we discuss the controlled integration of neural tools, more specifically generative tools, into the life cycle of a knowledge base: assistance with data localization/qualification, index extraction and aggregation, property suggestion and testing, dynamic file generation, and engineering of contextualized prompts (generic, contextual, explanatory, adjustment, procedural) aligned with a domain ontology. W e outline an ecosystem of specialized agents capable of animating the database while respe cting its symbolic constraints, by articulating model - driven and data - driven methods .

The rise of generative AI, has driven significant advancements in high-risk sectors like healthcare and finance. The Retrieval-Augmented Generation (RAG) architecture, combining language models (LLMs) with search engines, is particularly notable for its ability to generate responses from document corpora. Despite its potential, the reliability of RAG systems in critical contexts remains a concern, with issues such as hallucinations persisting. This study evaluates a RAG system used in due diligence for an investment fund. We propose a robust evaluation protocol combining human annotations and LLM-Judge annotations to identify system failures, like hallucinations, off-topic, failed citations, and abstentions. Inspired by the Prediction Powered Inference (PPI) method, we achieve precise performance measurements with statistical guarantees. We provide a comprehensive dataset for further analysis. Our contributions aim to enhance the reliability and scalability of RAG systems evaluation protocols in industrial applications.

Mots clés : c hinois l angue étrangère , i ntelligence a rtificielle , c onception de programmes d'enseignement avec ChatGPT , t âche communicative basée sur les conflits Title: Designing conflict - based communicative tasks in Teaching Chinese as a Foreign Language with ChatGPT Abstract: In developing the teaching program for a course in Oral Expression in Teaching Chinese as a Foreign Language at the university level, the teacher designs communicative tasks based on conflicts to encourage learners to engage in interactive dynamics and dev elop their oral interaction skills. During the design of these tasks, the teacher uses ChatGPT to assist in finalizing the program.

Multi-agent simulations enables the modeling and analyses of the dynamic behaviors and interactions of autonomous entities evolving in complex environments. Agent-based models (ABM) are widely used to study emergent phenomena arising from local interactions. However, their high computational cost poses a significant challenge, particularly for large-scale simulations requiring extensive parameter exploration, optimization, or uncertainty quantification. The increasing complexity of ABM limits their feasibility for real-time decision-making and large-scale scenario analysis. To address these limitations, surrogate models offer an efficient alternative by learning approximations from sparse simulation data. These models provide cheap-to-evaluate predictions, significantly reducing computational costs while maintaining accuracy. Various machine learning techniques, including regression models, neural networks, random forests and Gaussian processes, have been applied to construct robust surrogates. Moreover, uncertainty quantification and sensitivity analysis play a crucial role in enhancing model reliability and interpretability. This article explores the motivations, methods, and applications of surrogate modeling for ABM, emphasizing the trade-offs between accuracy, computational efficiency, and interpretability. Through a case study on a segregation model, we highlight the challenges associated with building and validating surrogate models, comparing different approaches and evaluating their performance. Finally, we discuss future perspectives on integrating surrogate models within ABM to improve scalability, explainability, and real-time decision support across various fields such as ecology, urban planning and economics.

1) Introduction and Conceptual Framework: This document explores the concept of information design by dividing it into two major practices: defining the meaning of a corpus of textual data and its visual or multimodal representation. It draws on expertise in enriching textual corpora, particularly audiovisual ones, and transforming them into multiple narrative formats. The text highlights a crucial distinction between the semantic content of a domain and the modalities of its graphic expression, illustrating this approach with concepts rooted in structural semiotics and linguistics traditions. 2) Modeling and Conceptual Design: The article emphasizes the importance of semantic modeling, often achieved through conceptual networks or graphs. These tools enable the structuring of knowledge within a domain by accounting for relationships between concepts, contexts of use, and specific objectives. Stockinger also highlights the constraints and challenges involved in creating dynamic and adaptable models, integrating elements such as thesauri or interoperable ontologies to facilitate the analysis and publication of complex corpora. 3) Applications and Multimodal Visualization: The text concludes by examining the practical application of these models in work environments like OKAPI, developed to analyze, publish, and reuse audiovisual data. It also discusses innovative approaches such as visual storytelling and document reengineering, which involve transforming existing content into new resources tailored to various contexts. These methods emphasize interoperability, flexibility, and the intelligence of communication systems, paving the way for richer and more collaborative use of digital data. The content of this document was presented during the "Semiotics of Information Design" Day organized by Anne Beyaert-Geslin of the University of Bordeaux Montaigne (MICA laboratory) on June 21, 2018, in Bordeaux.

This article explores assistive devices for upper limb movement in people with disabilities through a systematic review based on the PRISMA methodology. The studied devices encompass technologies ranging from orthoses to advanced robotics, aiming to compensate for or supplement motor impairments. The results highlight the diversity of applications (rehabilitation, daily living activities), targeted body segments (distal, proximal, or global), as well as control mechanisms and interfaces used. However, despite the variety of promising prototypes, few devices are commercially available, limiting their real impact on end users. Existing technologies, while effective in improving functional autonomy and quality of life, still face challenges in terms of ergonomics, cost, and portability. In conclusion, this article emphasizes the importance of a user-centered approach and proposes avenues for the development of innovative, modular, and accessible assistive devices.

Large Language Models (LLMs) like ChatGPT or Bard have revolutionized information retrieval and captivated the audience with their ability to generate custom responses in record time, regardless of the topic. In this article, we assess the capabilities of various LLMs in producing reliable, comprehensive, and sufficiently relevant responses about historical facts in French. To achieve this, we constructed a testbed comprising numerous history-related questions of varying types, themes, and levels of difficulty. Our evaluation of responses from ten selected LLMs reveals numerous shortcomings in both substance and form. Beyond an overall insufficient accuracy rate, we highlight uneven treatment of the French language, as well as issues related to verbosity and inconsistency in the responses provided by LLMs.