arXiv subjects

Albert Meroño-Peñuela

Publications and source records attributed to Albert Meroño-Peñuela.

16 recordsLinked to original sources

arXiv2026

Exploring the Design of GenAI-Based Systems to Support Socially Shared Metacognition

Socially shared metacognition (SSM) refers to the collective monitoring and regulation of joint cognitive processes in collaborative problem-solving, and is essential for effective knowledge work and learning. Generative AI (GenAI)-based systems offer new opportunities to support SSM, but emerging evidence suggests that poorly designed systems can encourage over-reliance on AI-generated explicit instruction and erode groups' capacity to develop autonomous regulatory processes. Group awareness tools (GATs) address this challenge through established design principles that make social and cognitive awareness information visible, highlight differences between group members to create cognitive conflict, and trigger autonomous elaboration and discussion, thereby implicitly guiding autonomous SSM emergence. This paper explores the design of GenAI-augmented GATs to support autonomous SSM in collaborative work and learning through an initial literature search, presenting preliminary design principles for discussion.

cs.HC↗

arXiv2025

Knowledge Prompting: How Knowledge Engineers Use Large Language Models

Despite many advances in knowledge engineering (KE), challenges remain in areas such as engineering knowledge graphs (KGs) at scale, keeping up with evolving domain knowledge, multilingualism, and multimodality. Recently, KE has used LLMs to support semi-automatic tasks, but the most effective use of LLMs to support knowledge engineers across the KE activites is still in its infancy. To explore the vision of LLM copilots for KE and change existing KE practices, we conducted a multimethod study during a KE hackathon. We investigated participants' views on the use of LLMs, the challenges they face, the skills they may need to integrate LLMs into their practices, and how they use LLMs responsibly. We found participants felt LLMs could contribute to improving efficiency when engineering KGs, but presented increased challenges around the already complex issues of evaluating the KE tasks. We discovered prompting to be a useful but undervalued skill for knowledge engineers working with LLMs, and note that natural language processing skills may become more relevant across more roles in KG construction. Integrating LLMs into KE tasks needs to be mindful of potential risks and harms related to responsible AI. Given the limited ethical training, most knowledge engineers receive solutions such as our suggested `KG cards' based on data cards could be a useful guide for KG construction. Our findings can support designers of KE AI copilots, KE researchers, and practitioners using advanced AI to develop trustworthy applications, propose new methodologies for KE and operate new technologies responsibly.

cs.HC↗

arXiv2025

How Far Are LLMs from Symbolic Planners? An NLP-Based Perspective

The reasoning and planning abilities of Large Language Models (LLMs) have been a frequent topic of discussion in recent years. Their ability to take unstructured planning problems as input has made LLMs' integration into AI planning an area of interest. Nevertheless, LLMs are still not reliable as planners, with the generated plans often containing mistaken or hallucinated actions. Existing benchmarking and evaluation methods investigate planning with LLMs, focusing primarily on success rate as a quality indicator in various planning tasks, such as validating plans or planning in relaxed conditions. In this paper, we approach planning with LLMs as a natural language processing (NLP) task, given that LLMs are NLP models themselves. We propose a recovery pipeline consisting of an NLP-based evaluation of the generated plans, along with three stages to recover the plans through NLP manipulation of the LLM-generated plans, and eventually complete the plan using a symbolic planner. This pipeline provides a holistic analysis of LLM capabilities in the context of AI task planning, enabling a broader understanding of the quality of invalid plans. Our findings reveal no clear evidence of underlying reasoning during plan generation, and that a pipeline comprising an NLP-based analysis of the plans, followed by a recovery mechanism, still falls short of the quality and reliability of classical planners. On average, only the first 2.65 actions of the plan are executable, with the average length of symbolically generated plans being 8.4 actions. The pipeline still improves action quality and increases the overall success rate from 21.9% to 27.5%.

cs.AI↗

arXiv2025

Hatevolution: What Static Benchmarks Don't Tell Us

Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking remains under-explored. Yet, hate speech benchmarks play a crucial role to ensure model safety. In this paper, we empirically evaluate the robustness of 20 language models across two evolving hate speech experiments, and we show the temporal misalignment between static and time-sensitive evaluations. Our findings call for time-sensitive linguistic benchmarks in order to correctly and reliably evaluate language models in the hate speech domain.

cs.CL↗

arXiv2025

Agreeing and Disagreeing in Collaborative Knowledge Graph Construction: An Analysis of Wikidata

In this work, we study disagreements in discussions around Wikidata, an online knowledge community that builds the data backend of Wikipedia. Discussions are essential in collaborative work as they can increase contributor performance and encourage the emergence of shared norms and practices. While disagreements can play a productive role in discussions, they can also lead to conflicts and controversies, which impact contributor' well-being and their motivation to engage. We want to understand if and when such phenomena arise in Wikidata, using a mix of quantitative and qualitative analyses to identify the types of topics people disagree about, the most common patterns of interaction, and roles people play when arguing for or against an issue. We find that decisions to create Wikidata properties are much faster than those to delete properties and that more than half of controversial discussions do not lead to consensus. Our analysis suggests that Wikidata is an inclusive community, considering different opinions when making decisions, and that conflict and vandalism are rare in discussions. At the same time, while one-fourth of the editors participating in controversial discussions contribute legitimate and insightful opinions about Wikidata's emerging issues, they respond with one or two posts and do not remain engaged in the discussions to reach consensus. Our work contributes to the analysis of collaborative KG construction with insights about communication and decision-making in projects, as well as with methodological directions and open datasets. We hope our findings will help managers and designers support community decision-making and improve discussion tools and practices.

cs.HC↗

arXiv2025

Towards Responsible AI Music: an Investigation of Trustworthy Features for Creative Systems

Generative AI is radically changing the creative arts, by fundamentally transforming the way we create and interact with cultural artefacts. While offering unprecedented opportunities for artistic expression and commercialisation, this technology also raises ethical, societal, and legal concerns. Key among these are the potential displacement of human creativity, copyright infringement stemming from vast training datasets, and the lack of transparency, explainability, and fairness mechanisms. As generative systems become pervasive in this domain, responsible design is crucial. Whilst previous work has tackled isolated aspects of generative systems (e.g., transparency, evaluation, data), we take a comprehensive approach, grounding these efforts within the Ethics Guidelines for Trustworthy Artificial Intelligence produced by the High-Level Expert Group on AI appointed by the European Commission - a framework for designing responsible AI systems across seven macro requirements. Focusing on generative music AI, we illustrate how these requirements can be contextualised for the field, addressing trustworthiness across multiple dimensions and integrating insights from the existing literature. We further propose a roadmap for operationalising these contextualised requirements, emphasising interdisciplinary collaboration and stakeholder engagement. Our work provides a foundation for designing and evaluating responsible music generation systems, calling for collaboration among AI experts, ethicists, legal scholars, and artists. This manuscript is accompanied by a website: https://amresearchlab.github.io/raim-framework/.

cs.AI↗

arXiv2025

Talking Wikidata: Communication patterns and their impact on community engagement in collaborative knowledge graphs

We study collaboration patterns of Wikidata, one of the world's largest open source collaborative knowledge graph (KG) communities. Collaborative KG communities, play a key role in structuring machine-readable knowledge to support AI systems like conversational agents. However, these communities face challenges related to long-term member engagement, as a small subset of contributors often is responsible for the majority of contributions and decision-making. While prior research has explored contributors' roles and lifespans, discussions within collaborative KG communities remain understudied. To fill this gap, we investigated the behavioural patterns of contributors and factors affecting their communication and participation. We analysed all the discussions on Wikidata using a mixed methods approach, including statistical tests, network analysis, and text and graph embedding representations. Our findings reveal that the interactions between Wikidata editors form a small world network, resilient to dropouts and inclusive, where both the network topology and discussion content influence the continuity of conversations. Furthermore, the account age of Wikidata members and their conversations are significant factors in their long-term engagement with the project. Our observations and recommendations can benefit the Wikidata and semantic web communities, providing guidance on how to improve collaborative environments for sustainability, growth, and quality.

cs.SI↗

arXiv2025

PathE: Leveraging Entity-Agnostic Paths for Parameter-Efficient Knowledge Graph Embeddings

Knowledge Graphs (KGs) store human knowledge in the form of entities (nodes) and relations, and are used extensively in various applications. KG embeddings are an effective approach to addressing tasks like knowledge discovery, link prediction, and reasoning. This is often done by allocating and learning embedding tables for all or a subset of the entities. As this scales linearly with the number of entities, learning embedding models in real-world KGs with millions of nodes can be computationally intractable. To address this scalability problem, our model, PathE, only allocates embedding tables for relations (which are typically orders of magnitude fewer than the entities) and requires less than 25% of the parameters of previous parameter efficient methods. Rather than storing entity embeddings, we learn to compute them by leveraging multiple entity-relation paths to contextualise individual entities within triples. Evaluated on four benchmarks, PathE achieves state-of-the-art performance in relation prediction, and remains competitive in link prediction on path-rich KGs while training on consumer-grade hardware. We perform ablation experiments to test our design choices and analyse the sensitivity of the model to key hyper-parameters. PathE is efficient and cost-effective for relationally diverse and well-connected KGs commonly found in real-world applications.

cs.AI↗

arXiv2025

How an AI-ready National Data Library would help UK science

In this paper, we provide a technical vision for key enabling elements for the architecture of the UK National Data Library (NDL) with a strong focus on building it as an AI-ready data infrastructure through standardised vocabularies, automated analysis tools, and interoperability services. We follow the ODI Multilayer Interoperability Framework (MIF) for data stewardship, covering central socio-technical aspects for the NDL including user-centric approaches to service design and governance.

cs.DL↗

arXiv2024

Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for ORE that utilises large language models (LLMs) to streamline the process through four key functions: user story creation, competency question (CQ) extraction, CQ filtration and analysis, and ontology testing support. In OntoChat, users are expected to prompt the chatbot to generate user stories. However, preliminary evaluations revealed that they struggle to do this effectively. To address this issue, we experimented with a research method called participatory prompting, which involves researcher-mediated interactions to help users without deep knowledge of LLMs use the chatbot more effectively. This participatory prompting user study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories. These refined user stories will subsequently be converted into CQs.

cs.HC↗

arXiv2024

User Experience In Dataset Search

This research investigates User Experience (UX) issues in dataset search, targeting Google Dataset Search and data.europa.eu. It focuses on 6 areas within UX: Initial Interaction, Search Process, Dataset Exploration, Filtering and Sorting, Dataset Actions, and Assistance and Feedback. The evaluation method combines 'The Pandemic Puzzle' user task, think-aloud methods, and demographic and post-task questionnaires. 29 strengths and 63 weaknesses were collected from 19 participants involved in roles within technology firm or academia. While certain insights are specific to particular platforms, most are derived from features commonly observed in dataset search platforms across a variety of fields, implying that our findings are broadly applicable. Observations from commonly found features in dataset search platforms across various fields have led to the development of 10 new design prototypes. Unlike literature retrieval, dataset retrieval involves a significant focus on metadata accessibility and quality, each element of which can impact decision-making. To address issues like reading fatigue from metadata presentation, inefficient methods for results searching, filtering, and selection, along with other unresolved user-centric issues on current platforms. These prototypes concentrate on enhancing metadata-related features. They include a redesigned homepage, an improved search bar, better sorting options, an enhanced search result display, a metadata comparison tool, and a navigation guide. Our aim is to improve usability for a wide range of users, including both developers and researchers.

cs.HC↗

arXiv2023

The Music Meta Ontology: a flexible semantic model for the interoperability of music metadata

The semantic description of music metadata is a key requirement for the creation of music datasets that can be aligned, integrated, and accessed for information retrieval and knowledge discovery. It is nonetheless an open challenge due to the complexity of musical concepts arising from different genres, styles, and periods -- standing to benefit from a lingua franca to accommodate various stakeholders (musicologists, librarians, data engineers, etc.). To initiate this transition, we introduce the Music Meta ontology, a rich and flexible semantic model to describe music metadata related to artists, compositions, performances, recordings, and links. We follow eXtreme Design methodologies and best practices for data engineering, to reflect the perspectives and the requirements of various stakeholders into the design of the model, while leveraging ontology design patterns and accounting for provenance at different levels (claims, links). After presenting the main features of Music Meta, we provide a first evaluation of the model, alignments to other schema (Music Ontology, DOREMUS, Wikidata), and support for data transformation.

cs.IR↗

arXiv2023

The Music Annotation Pattern

The annotation of music content is a complex process to represent due to its inherent multifaceted, subjectivity, and interdisciplinary nature. Numerous systems and conventions for annotating music have been developed as independent standards over the past decades. Little has been done to make them interoperable, which jeopardises cross-corpora studies as it requires users to familiarise with a multitude of conventions. Most of these systems lack the semantic expressiveness needed to represent the complexity of the musical language and cannot model multi-modal annotations originating from audio and symbolic sources. In this article, we introduce the Music Annotation Pattern, an Ontology Design Pattern (ODP) to homogenise different annotation systems and to represent several types of musical objects (e.g. chords, patterns, structures). This ODP preserves the semantics of the object's content at different levels and temporal granularity. Moreover, our ODP accounts for multi-modality upfront, to describe annotations derived from different sources, and it is the first to enable the integration of music datasets at a large scale.

cs.AI↗

arXiv2020

Ontologies in CLARIAH: Towards Interoperability in History, Language and Media

One of the most important goals of digital humanities is to provide researchers with data and tools for new research questions, either by increasing the scale of scholarly studies, linking existing databases, or improving the accessibility of data. Here, the FAIR principles provide a useful framework as these state that data needs to be: Findable, as they are often scattered among various sources; Accessible, since some might be offline or behind paywalls; Interoperable, thus using standard knowledge representation formats and shared vocabularies; and Reusable, through adequate licensing and permissions. Integrating data from diverse humanities domains is not trivial, research questions such as "was economic wealth equally distributed in the 18th century?", or "what are narratives constructed around disruptive media events?") and preparation phases (e.g. data collection, knowledge organisation, cleaning) of scholars need to be taken into account. In this chapter, we describe the ontologies and tools developed and integrated in the Dutch national project CLARIAH to address these issues across datasets from three fundamental domains or "pillars" of the humanities (linguistics, social and economic history, and media studies) that have paradigmatic data representations (textual corpora, structured data, and multimedia). We summarise the lessons learnt from using such ontologies and tools in these domains from a generalisation and reusability perspective.

cs.AI↗

arXiv2018

Nanopublications: A Growing Resource of Provenance-Centric Scientific Linked Data

Nanopublications are a Linked Data format for scholarly data publishing that has received considerable uptake in the last few years. In contrast to the common Linked Data publishing practice, nanopublications work at the granular level of atomic information snippets and provide a consistent container format to attach provenance and metadata at this atomic level. While the nanopublications format is domain-independent, the datasets that have become available in this format are mostly from Life Science domains, including data about diseases, genes, proteins, drugs, biological pathways, and biotic interactions. More than 10 million such nanopublications have been published, which now form a valuable resource for studies on the domain level of the given Life Science domains as well as on the more technical levels of provenance modeling and heterogeneous Linked Data. We provide here an overview of this combined nanopublication dataset, show the results of some overarching analyses, and describe how it can be accessed and queried.

cs.DL↗

arXiv2015

Release Early, Release Often: Predicting Change in Versioned Knowledge Organization Systems on the Web

The Semantic Web is built on top of Knowledge Organization Systems (KOS) (vocabularies, ontologies, concept schemes) that provide a structured, interoperable and distributed access to Linked Data on the Web. The maintenance of these KOS over time has produced a number of KOS version chains: subsequent unique version identifiers to unique states of a KOS. However, the release of new KOS versions pose challenges to both KOS publishers and users. For publishers, updating a KOS is a knowledge intensive task that requires a lot of manual effort, often implying deep deliberation on the set of changes to introduce. For users that link their datasets to these KOS, a new version compromises the validity of their links, often creating ramifications. In this paper we describe a method to automatically detect which parts of a Web KOS are likely to change in a next version, using supervised learning on past versions in the KOS version chain. We use a set of ontology change features to model and predict change in arbitrary Web KOS. We apply our method on 139 varied datasets systematically retrieved from the Semantic Web, obtaining robust results at correctly predicting change. To illustrate the accuracy, genericity and domain independence of the method, we study the relationship between its effectiveness and several characterizations of the evaluated datasets, finding that predictors like the number of versions in a chain and their release frequency have a fundamental impact in predictability of change in Web KOS. Consequently, we argue for adopting a release early, release often philosophy in Web KOS development cycles.

cs.AI↗