arXiv subjects

Albert Meroño Peñuela

Publications and source records attributed to Albert Meroño Peñuela.

4 recordsLinked to original sources

arXiv2026

Design Guidance Towards Addressing Over-Reliance on AI in Sensemaking

Sensemaking in collaborative work and learning is increasingly supported by GenAI systems, however, emerging evidence suggests that poorly designed GenAI systems tend to provide explicit instruction that groups passively follow, fostering over-reliance and eroding autonomous sensemaking. Group awareness tools (GATs) address this challenge through implicit guidance: rather than instructing groups on what to do, GATs externalize observable collaboration data through visualizations that reveal differences between group members to create cognitive conflict, which triggers autonomous elaboration and discussion, thereby implicitly guiding autonomous sensemaking emergence. Drawing on an initial literature search of existing GAT systems, this paper explores the design of GenAI-augmented GATs to support autonomous sensemaking in collaborative work and learning, presenting preliminary design principles for discussion.

cs.HC↗

arXiv2025

Schema Generation for Large Knowledge Graphs Using Large Language Models

Schemas play a vital role in ensuring data quality and supporting usability in the Semantic Web and natural language processing. Traditionally, their creation demands substantial involvement from knowledge engineers and domain experts. Leveraging the impressive capabilities of large language models (LLMs) in tasks like ontology engineering, we explore schema generation using LLMs. To bridge the resource gap, we introduce two datasets: YAGO Schema and Wikidata EntitySchema, along with novel evaluation metrics. The LLM-based pipelines utilize local and global information from knowledge graphs (KGs) to generate schemas in Shape Expressions (ShEx). Experiments demonstrate LLMs' strong potential in producing high-quality ShEx schemas, paving the way for scalable, automated schema generation for large KGs. Furthermore, our benchmark introduces a new challenge for structured generation, pushing the limits of LLMs on syntactically rich formalisms.

cs.AI↗

arXiv2025

Filling in the Blanks? A Systematic Review and Theoretical Conceptualisation for Measuring WikiData Content Gaps

Wikidata is a collaborative knowledge graph which provides machine-readable structured data for Wikimedia projects including Wikipedia. Managed by a community of volunteers, it has grown to become the most edited Wikimedia project. However, it features a long-tail of items with limited data and a number of systematic gaps within the available content. In this paper, we present the results of a systematic literature review aimed to understand the state of these content gaps within Wikidata. We propose a typology of gaps based on prior research and contribute a theoretical framework intended to conceptualise gaps and support their measurement. We also describe the methods and metrics present used within the literature and classify them according to our framework to identify overlooked gaps that might occur in Wikidata. We then discuss the implications for collaboration and editor activity within Wikidata as well as future research directions. Our results contribute to the understanding of quality, completeness and the impact of systematic biases within Wikidata and knowledge gaps more generally.

cs.SI↗

arXiv2023

Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata

In this work, we explore the use of Large Language Models (LLMs) for knowledge engineering tasks in the context of the ISWC 2023 LM-KBC Challenge. For this task, given subject and relation pairs sourced from Wikidata, we utilize pre-trained LLMs to produce the relevant objects in string format and link them to their respective Wikidata QIDs. We developed a pipeline using LLMs for Knowledge Engineering (LLMKE), combining knowledge probing and Wikidata entity mapping. The method achieved a macro-averaged F1-score of 0.701 across the properties, with the scores varying from 1.00 to 0.328. These results demonstrate that the knowledge of LLMs varies significantly depending on the domain and that further experimentation is required to determine the circumstances under which LLMs can be used for automatic Knowledge Base (e.g., Wikidata) completion and correction. The investigation of the results also suggests the promising contribution of LLMs in collaborative knowledge engineering. LLMKE won Track 2 of the challenge. The implementation is available at https://github.com/bohuizhang/LLMKE.

cs.CL↗