Pascal Molli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pascal Molli has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Hala Skaf-Molli
Nantes Université, CNRS, LS2N
27 shared publications - Brice Nédelec
Nantes Université, CNRS, LS2N
8 shared publications Hala Skaf-Molli
Nantes Université - LS2N
6 shared publications- Julien Aimonier-Davat
Nantes Université, CNRS, LS2N
6 shared publications - Gérald Oster
Univ Henri Poincare, Univ Lorraine, INRIA, LORIA,Score Team, Sophia Antipolis, France
5 shared publications - Maria-Esther Vidal
TIB Leibniz Information Centre for Science and Technology
5 shared publications
Latest Publications
- 23 October 2026
- Published by Springer Nature
- p. 333-361
KARMA: When Knowledge Graphs Still Matter for Retrieval-Augmented Question Answering
- 23 October 2026
- Published by Springer Nature
- p. 333-361
KARMA: When Knowledge Graphs Still Matter for Retrieval-Augmented Question Answering
- 23 October 2026
- Published by Springer Nature
- p. 362-391
FeDivers: Graph-Pattern-Aware Source Selection for Scalable SPARQL Federations
- 23 October 2026
- Published by Springer Nature
- p. 362-391
FeDivers: Graph-Pattern-Aware Source Selection for Scalable SPARQL Federations
- Open Access
- 6 November 2025
- Published by SAGE Publications in Semantic Web: – Interoperability, Usability, Applicability
- Vol. 16 (6)
LLM4Schema.org: Generating Schema.org Markups With Large Language Models
Integrating Schema.org markup into web pages has resulted in the generation of billions of RDF triples. However, around 75% of web pages still lack this critical markup. Large language models (LLMs) present a promising solution by automatically generating the missing Schema.org markup. Despite this potential, there is currently no benchmark to evaluate the markup quality produced by LLMs. This article introduces LLM4Schema.org, an innovative approach for assessing the performance of LLMs in generating Schema.org markup. Unlike traditional methods, LLM4Schema.org does not require a predefined ground truth. Instead, it compares the quality of LLM-generated markup against human-generated markup. Our findings reveal that 40%–50% of the markup produced by GPT-3.5 and GPT-4 is invalid, non-factual, or non-compliant with the Schema.org ontology. These errors underscore the limitations of LLMs in adhering strictly to structured ontologies like Schema.org without additional filtering and validation mechanisms. We demonstrate that specialized LLM-powered agents can effectively identify and eliminate these errors. After applying such filtering for both human and LLM-generated markup, GPT-4 shows notable improvements in quality and outperforms humans. LLM4Schema.org highlights both the potential and the challenges of leveraging LLMs for semantic annotations, emphasizing the critical role of careful curation and validation to achieve reliable results.
- 6 November 2025
- Published by SAGE Publications in Semantic Web: – Interoperability, Usability, Applicability
- Vol. 16 (6)
Open AccessLLM4Schema.org: Generating Schema.org Markups With Large Language Models
Integrating Schema.org markup into web pages has resulted in the generation of billions of RDF triples. However, around 75% of web pages still lack this critical markup. Large language models (LLMs) present a promising solution by automatically generating the missing Schema.org markup. Despite this potential, there is currently no benchmark to evaluate the markup quality produced by LLMs. This article introduces LLM4Schema.org, an innovative approach for assessing the performance of LLMs in generating Schema.org markup. Unlike traditional methods, LLM4Schema.org does not require a predefined ground truth. Instead, it compares the quality of LLM-generated markup against human-generated markup. Our findings reveal that 40%–50% of the markup produced by GPT-3.5 and GPT-4 is invalid, non-factual, or non-compliant with the Schema.org ontology. These errors underscore the limitations of LLMs in adhering strictly to structured ontologies like Schema.org without additional filtering and validation mechanisms. We demonstrate that specialized LLM-powered agents can effectively identify and eliminate these errors. After applying such filtering for both human and LLM-generated markup, GPT-4 shows notable improvements in quality and outperforms humans. LLM4Schema.org highlights both the potential and the challenges of leveraging LLMs for semantic annotations, emphasizing the critical role of careful curation and validation to achieve reliable results.
- 13 October 2025
- Published by Springer Nature
- p. 103-107
SparqLLM: Retrieval-Augmented SPARQL Query Processing
- 13 October 2025
- Published by Springer Nature
- p. 103-107
SparqLLM: Retrieval-Augmented SPARQL Query Processing
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 47-58
Passage: Ensuring Completeness and Responsiveness of Public SPARQL Endpoints with SPARQL Continuation Queries
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 47-58
Open AccessPassage: Ensuring Completeness and Responsiveness of Public SPARQL Endpoints with SPARQL Continuation Queries
- 27 November 2024
- Published by Springer Nature
- p. 98-115
CRAWD: Sampling-Based Estimation of Count-Distinct SPARQL Queries
- 27 November 2024
- Published by Springer Nature
- p. 98-115
CRAWD: Sampling-Based Estimation of Count-Distinct SPARQL Queries
- Open Access
- 11 September 2024
- Published by IOS Press
- p. 279-293
Enabling Delayed-Answer Auctions for RDF Knowledge Graphs Monetisation
Traditionally, querying knowledge graphs is free of charge. However, ensuring data and service availability incurs costs to knowledge graphs providers. The Delayed-Answer Auction (DAA) model has been proposed to fund the maintenance of knowledge graph endpoints by allowing customers to sponsor entities in the Knowledge Graph so query results that include them are delivered in priority. However, implementing DAA with time-to-first results acceptable for data consumers is challenging because it requires reordering results according to bid values. In this paper, we present the AuctionKG approach to enable DAA with a low impact on query execution performance. AuctionKG relies on (i) reindexing sponsored entities by bid values to ensure they are processed first and (ii) Web preemption to ensure delayed answering. Experimental results demonstrate that our approach outperforms a baseline approach to enable DAA in terms of time for first results.
- 11 September 2024
- Published by IOS Press
- p. 279-293
Open AccessEnabling Delayed-Answer Auctions for RDF Knowledge Graphs Monetisation
Traditionally, querying knowledge graphs is free of charge. However, ensuring data and service availability incurs costs to knowledge graphs providers. The Delayed-Answer Auction (DAA) model has been proposed to fund the maintenance of knowledge graph endpoints by allowing customers to sponsor entities in the Knowledge Graph so query results that include them are delivered in priority. However, implementing DAA with time-to-first results acceptable for data consumers is challenging because it requires reordering results according to bid values. In this paper, we present the AuctionKG approach to enable DAA with a low impact on query execution performance. AuctionKG relies on (i) reindexing sponsored entities by bid values to ensure they are processed first and (ii) Web preemption to ensure delayed answering. Experimental results demonstrate that our approach outperforms a baseline approach to enable DAA in terms of time for first results.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2315-2324
FedUP: Querying Large-Scale Federations of SPARQL Endpoints
Processing SPARQL queries over large federations of SPARQL endpoints is crucial for keeping the Semantic Web decentralized. Despite the existence of hundreds of SPARQL endpoints, current federation engines only scale to dozens. One major issue comes from the current definition of the source selection problem, i.e., finding the minimal set of SPARQL endpoints to contact per triple pattern. Even if such a source selection is minimal, only a few combinations of sources may return results. Consequently, most of the query processing time is wasted evaluating combinations that return no results. In this paper, we introduce the concept of Result-Aware query plans. This concept ensures that every subquery of the query plan effectively contributes to the result of the query. To compute a Result-Aware query plan, we propose FedUP, a new federation engine able to produce Result-Aware query plans by tracking the provenance of query results. However, getting query results requires computing source selection, and computing source selection requires query results. To break this vicious cycle, FedUP computes results and provenances on tiny quotient summaries of federations at the cost of source selection accuracy. Experimental results on federated benchmarks demonstrate that FedUP outperforms state-of-the-art federation engines by orders of magnitude in the context of large-scale federations.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2315-2324
Open AccessFedUP: Querying Large-Scale Federations of SPARQL Endpoints
Processing SPARQL queries over large federations of SPARQL endpoints is crucial for keeping the Semantic Web decentralized. Despite the existence of hundreds of SPARQL endpoints, current federation engines only scale to dozens. One major issue comes from the current definition of the source selection problem, i.e., finding the minimal set of SPARQL endpoints to contact per triple pattern. Even if such a source selection is minimal, only a few combinations of sources may return results. Consequently, most of the query processing time is wasted evaluating combinations that return no results. In this paper, we introduce the concept of Result-Aware query plans. This concept ensures that every subquery of the query plan effectively contributes to the result of the query. To compute a Result-Aware query plan, we propose FedUP, a new federation engine able to produce Result-Aware query plans by tracking the provenance of query results. However, getting query results requires computing source selection, and computing source selection requires query results. To break this vicious cycle, FedUP computes results and provenances on tiny quotient summaries of federations at the cost of source selection accuracy. Experimental results on federated benchmarks demonstrate that FedUP outperforms state-of-the-art federation engines by orders of magnitude in the context of large-scale federations.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 617-620
Online Sampling of Summaries from Public SPARQL Endpoints
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 617-620
Open AccessOnline Sampling of Summaries from Public SPARQL Endpoints
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1059-1062
Fediscount: Shopping Online at a Federated Store Using FedUP as SPARQL Federation Engine
Processing SPARQL queries over large federations of SPARQL endpoints is essential for maintaining the Semantic Web decentralized. However, existing federation engines struggle to query more than a dozen of endpoints. We recently proposed FedUP, a new type of federation engine based on unions-over-joins query plans that outperforms state-of-the-art federation engines by orders of magnitude on large federations. This demonstration paper introduces Fediscount, a federated online shopping application based on the FedShop benchmark, illustrating the capabilities of FedUP. The application is based on standard Semantic Web technologies, enabling end-users to shop online in a virtual federated store comprising 20, 100, or even 200 SPARQL endpoints. This breakthrough opens up promising new avenues for developing and deploying federated applications.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1059-1062
Open AccessFediscount: Shopping Online at a Federated Store Using FedUP as SPARQL Federation Engine
Processing SPARQL queries over large federations of SPARQL endpoints is essential for maintaining the Semantic Web decentralized. However, existing federation engines struggle to query more than a dozen of endpoints. We recently proposed FedUP, a new type of federation engine based on unions-over-joins query plans that outperforms state-of-the-art federation engines by orders of magnitude on large federations. This demonstration paper introduces Fediscount, a federated online shopping application based on the FedShop benchmark, illustrating the capabilities of FedUP. The application is based on standard Semantic Web technologies, enabling end-users to shop online in a virtual federated store comprising 20, 100, or even 200 SPARQL endpoints. This breakthrough opens up promising new avenues for developing and deploying federated applications.