Fabien Gandon

Guillaume Méroué, Fabien Gandon, Pierre Monnin

Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs. Standard evaluation protocols emphasize rank-based metrics such as MRR or Hits@$K$, but usually overlook the influence of random seeds on result stability. Moreover, these metrics conceal potential instabilities in individual predictions and in the organization of embedding spaces. In this work, we conduct a systematic stability analysis of multiple KGEMs across several datasets. We find that high-performance models actually produce divergent predictions at the triple level and highly variable embedding spaces. By isolating stochastic factors (i.e., initialization, triple ordering, negative sampling, dropout, hardware), we show that each independently induces instability of comparable magnitude. Furthermore, for a given model, hyperparameter configurations with better MRR are not guaranteed to be more stable. Moreover, voting, albeit a known remediation mechanism, only provides a limited enhancement of stability. These findings highlight critical limitations of current benchmarking protocols, and raise concerns about the reliability of KGEMs for knowledge graph completion.

Martin Legrand, Tao Jiang, Matthieu Feraud et al.

Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that invoke available tools and scientific software libraries, and scores executions with an LLM-based judge whose feedback drives workflow refinement. On ScienceAgentBench, Mimosa achieves a success rate of 43.1% with DeepSeek-V3.2, surpassing both single-agent baselines and static multi-agent configurations. Our results further reveal that models respond heterogeneously to multi-agent decomposition and iterative learning, indicating that the benefits of workflow evolution depend on the capabilities of the underlying execution model. Beyond these benchmarks, Mimosa modular architecture and tool-agnostic design make it readily extensible, and its fully logged execution traces and archived workflows support auditability by preserving every analytical step for inspection and potential replication. Combined with domain-expert guidance, the framework has the potential to automate a broad range of computationally accessible scientific tasks across disciplines. Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.

Matthieu Féraud, Dina Boukhajou, Fabien Gandon et al.

Untargeted metabolomics generates large volumes of tandem mass spectrometry (MS/MS) data and computational annotations that can reveal molecular mechanisms across organisms and environments. Public reuse has improved through harmonized repository metadata and access infrastructures such as Pan-ReDU, and through metabolomics knowledge graphs such as ENPKG and METRIN-KG. Yet the analytical layer remains fragmented: spectra, features, workflow outputs, annotations, confidence evidence, and contextual metadata are still scattered across repositories and tabular artifacts. We present MetaboKG, an analysis-centric knowledge graph framework for engineering reusable metabolomics knowledge from public repositories, metadata, and GNPS molecular network results. MetaboKG contributes a transformation workflow that preserves links between repository exports, analytical files, spectra, features, and annotation results; a semantic model grounded in PROV-O and SIO and aligned with the Mass Spectrometry ontology (MS), ChEBI, NCBITaxon, ENVO, and NCIT to represent provenance, analytical evidence, metadata attributes, and controlled vocabulary terms; and a Universal Annotation Identifier strategy extending the Universal Spectrum Identifier (USI) with workflow-specific components for late binding, incremental ingestion, and post hoc linkage across analyses. We demonstrate MetaboKG at the public-repository scale on 680 GNPS molecular networking results and evaluate it through competency questions covering biochemical enrichment, environmental specificity, and cross instrument analytical variation. Results show that graph-based integration supports traceable annotation reuse and reproducible SPARQL exploration of biochemical relationships that remain fragmented across repository-native resources.

Ndeye-Emilie Mbengue, Pierre Monnin, Miguel Couceiro et al.

Emerging digital technologies are exacerbating the existing divide in Open Access Data (OAD) between high-and low-resource languages, excluding many communities from the global digital transformation. Multilingual Linked Open Data Knowledge Graphs (LOD KGs) could contribute to mitigating this divide through cross-lingual transfer; however, no clear quantitative definition of low-resource languages has yet been established in the context of LOD KGs. In this poster, we present a methodology to analyze the distribution of languages across LOD KGs and propose a preliminary multi-level categorization based on DBpedia, BabelNet, and Wikidata. This categorization is leveraged to bring a formal definition of low-, high-, and medium-resource languages that could be later leveraged to select cross-lingual transfer candidates.

Yousouf Taghzouti, Tao Jiang, Camille Juigné et al.

The evaluation of Question Answering (QA) systems over Knowledge Graphs has historically suffered from fragmentation, inconsistency, and limited reproducibility. While significant progress has been made in semantic parsing and SPARQL query generation, evaluation methodologies remain diverse, ad hoc, and often incomparable across studies. Existing benchmarks typically focus on a small subset of metrics, such as query exact match or answer-level F1, neglecting syntactic validity, semantic faithfulness, execution correctness, results ranking quality, and computational efficiency. In this paper, we present t2s-metrics, an open-source, extensible, and unified evaluation library designed specifically for SPARQL query comparison and execution-based assessment. t2s-metrics provides a broad and extensible set of over 20 evaluation metrics, collected from the literature and practical evaluation needs, spanning lexical, syntactic, semantic, structural, execution-based and ranking-based dimensions. These include query-based metrics such as token-level Precision, Recall, and F1; BLEU, ROUGE, METEOR, and CodeBLEU variants; variable-normalized metrics (SP-BLEU, SP-F1); graph-and URI-based exact match metrics; as well as answer set-based metrics such as F1-QALD and Jaccard similarity; ranking metrics including MRR, NDCG, P@k, and Hit@k; and LLM-as-a-Judge metrics. Taking inspiration from the ir-metrics library for Information Retrieval, t2s-metrics provides a modular abstraction layer that decouples metric specification from implementation, enabling consistent, transparent, and reproducible evaluation of SPARQLbased QA systems. We argue that t2s-metrics constitutes a necessary step toward systematic, standardized evaluation in question answering over knowledge graphs and facilitates deeper diagnostic insights into system behavior beyond answer correctness.

Madina Bekbergenova, Lucas Pradi, Benjamin Navet et al.

Mass spectrometry metabolomics generates vast amounts of data requiring advanced methods for interpretation. Knowledge graphs address these challenges by structuring mass spectrometry data, metabolite information, and their relationships into a connected network (Gaudry et al. 2024). However, effective use of a knowledge graph demands an in-depth understanding of its ontology and its query language syntax. To overcome this, we designed MetaboT, an AI system utilizing large language models (LLMs) to translate user questions into SPARQL semantic query language for operating on knowledge graphs (Steve Harris 2013). We demonstrate its effectiveness using the Experimental Natural Products Knowledge Graph (ENPKG), a large-scale public knowledge graph for plant natural products (Gaudry et al. 2024).MetaboT employs specialized AI agents for handling user queries and interacting with the knowledge graph by breaking down complex tasks into discrete components, each managed by a specialised agent (Fig. 1a). The multi-agent system is constructed using the LangChain and LangGraph libraries, which facilitate the integration of LLMs with external tools and information sources (LangChain, n.d.). The query generation process follows a structured workflow. First, the Entry Agent determines if the question is new or a follow-up to previous interactions. New questions are forwarded to the Validator Agent, which verifies if the question is related to the knowledge graph. Then, the valid question is sent to the Supervisor Agent, which identifies if the question requires chemical conversions or standardized identifiers. In this case it delegates the question to the Knowledge Graph Agent, which can use tools to extract necessary details, such as URIs or taxonomies of chemical names, from the user query. Finally, an agent responsible for crafting the SPARQL queries equipped with the ontology of the knowledge graph uses the provided identifiers to generate the query. Then, the system executes the generated query against the metabolomics knowledge graph and returns structured results to the user (Fig. 1b). To assess the performance of MetaboT we have curated 50 metabolomics-related questions and their expected answers. In addition to submitting these questions to MetaboT, we evaluated a baseline by submitting them to a standard LLM (GPT-4o) with a prompt that incorporated the knowledge graph ontology but did not provide specific entity IDs. This baseline achieved only 8.16% accuracy, compared to MetaboT's 83.67%, underscoring the necessity of our multi-agent system for accurately retrieving entities and generating correct SPARQL queries. MetaboT demonstrates promising performance as a conversational question-answering assistant, enabling researchers to retrieve structured metabolomics data through natural language queries. By automating the generation and execution of SPARQL queries, it removes technical barriers that have traditionally hindered access to knowledge graphs. Importantly, MetaboT leverages the capabilities of LLMs while maintaining experimentally grounded query generation, ensuring that outputs remain aligned with domain-specific standards and data structures. This approach facilitates data-driven discoveries by bridging the gap between complex semantic technologies and user-friendly interaction. MetaboT is accessible at [https://metabot.holobiomicslab.eu/], and its source code is available at [https://github.com/HolobiomicsLab/MetaboT].

Yousouf Taghzouti, Franck Michel, Tao Jiang et al.

The SPARQL query language is the standard method to access knowledge graphs (KGs). However, formulating SPARQL queries is a significant challenge for non-expert users, and remains time-consuming for the experienced ones. Best practices recommend to document KGs with competency questions and example queries to contextualise the knowledge they contain and illustrate their potential applications. In practice, however, this is either not the case or the examples are provided in limited numbers. Large Language Models (LLMs) are being used in conversational agents and are proving to be an attractive solution with a wide range of applications, from simple question-answering about common knowledge to generating code in a targeted programming language. However, training and testing these models to produce high quality SPARQL queries from natural language questions requires substantial datasets of question-query pairs. In this paper, we present Q${}^2$Forge that addresses the challenge of generating new competency questions for a KG and corresponding SPARQL queries. It iteratively validates those queries with human feedback and LLM as a judge. Q${}^2$Forge is open source, generic, extensible and modular, meaning that the different modules of the application (CQ generation, query generation and query refinement) can be used separately, as an integrated pipeline, or replaced by alternative services. The result is a complete pipeline from competency question formulation to query evaluation, supporting the creation of reference query sets for any target KG.

Célian Ringwald, Fabien Gandon, Catherine Faron et al.

Small language models (SLMs) have shown promises for relation extraction (RE) when extracting RDF triples guided by SHACL shapes focused on common datatype properties. This paper investigates how SLMs handle both datatype and object properties for a complete RDF graph extraction. We show that the key bottleneck is related to long-tail distribution of rare properties. To solve this issue, we evaluate several strategies: stratified sampling, weighted loss, dataset scaling, and template-based synthetic data augmentation. We show that the best strategy to perform equally well over unbalanced target properties is to build a training set where the number of occurrences of each property exceeds a given threshold. To enable reproducibility, we publicly released our datasets, experimental results and code. Our findings offer practical guidance for training shape-aware SLMs and highlight promising directions for future work in semantic RE.

Michael Fell, Elena Cabrio, Elmahdi Korfed et al.

We present the WASABI Song Corpus, a large corpus of songs enriched with metadata extracted from music databases on the Web, and resulting from the processing of song lyrics and from audio analysis. More specifically, given that lyrics encode an important part of the semantics of a song, we focus here on the description of the methods we proposed to extract relevant information from the lyrics, such as their structure segmentation, their topics, the explicitness of the lyrics content, the salient passages of a song and the emotions conveyed. The creation of the resource is still ongoing: so far, the corpus contains 1.73M songs with lyrics (1.41M unique lyrics) annotated at different levels with the output of the above mentioned methods. Such corpus labels and the provided methods can be exploited by music search engines and music professionals (e.g. journalists, radio presenters) to better handle large collections of lyrics, allowing an intelligent browsing, categorization and segmentation recommendation of songs.

Fabien Gandon, Franck Michel, Olivier Corby et al.

This article is a collective position paper from the Wimmics research team, expressing our vision of how Web graph data technologies should evolve in the future in order to ensure a high-level of interoperability between the many types of applications that produce and consume graph data. Wimmics stands for Web-Instrumented Man-Machine Interactions, Communities, and Semantics. We are a joint research team between INRIA Sophia Antipolis-M{é}diterran{é}e and I3S (CNRS and Universit{é} C{ô}te d'Azur). Our challenge is to bridge formal semantics and social semantics on the web. Our research areas are graph-oriented knowledge representation, reasoning and operationalization to model and support actors, actions and interactions in web-based epistemic communities. The application of our research is supporting and fostering interactions in online communities and management of their resources. In this position paper, we emphasize the need to extend the semantic Web standard stack to address and fulfill new graph data needs, as well as the importance of remaining compatible with existing recommendations, in particular the RDF stack, to avoid the painful duplication of models, languages, frameworks, etc. The following sections group motivations for different directions of work and collect reasons for the creation of a working group on RDF 2.0 and other recommendations of the RDF family.

Cédric Lopez, Molka Dhouib, Elena Cabrio et al.

As part of the SMILK Joint Lab, we studied the use of Natural Language Processing to: (1) enrich knowledge bases and link data on the web, and conversely (2) use this linked data to contribute to the improvement of text analysis and the annotation of textual content, and to support knowledge extraction. The evaluation focused on brand-related information retrieval in the field of cosmetics. This article describes each step of our approach: the creation of ProVoc, an ontology to describe products and brands; the automatic population of a knowledge base mainly based on ProVoc from heterogeneous textual resources; and the evaluation of an application which that takes the form of a browser plugin providing additional knowledge to users browsing the web.

Maxime Lefrançois, Fabien Gandon

We are interested in bridging the world of natural language and the world of the semantic web in particular to support natural multilingual access to the web of data. In this paper we introduce a new type of lexical ontology called interlingual lexical ontology (ILexicOn), which uses semantic web formalisms to make each interlingual lexical unit class (ILUc) support the projection of its semantic decomposition on itself. After a short overview of existing lexical ontologies, we briefly introduce the semantic web formalisms we use. We then present the three layered architecture of our approach: i) the interlingual lexical meta-ontology (ILexiMOn); ii) the ILexicOn where ILUcs are formally defined; iii) the data layer. We illustrate our approach with a standalone ILexicOn, and introduce and explain a concise human-readable notation to represent ILexicOns. Finally, we show how semantic web formalisms enable the projection of a semantic decomposition on the decomposed ILUc.