arXiv subjects

Paul T. Groth

Publications and source records attributed to Paul T. Groth.

3 recordsLinked to original sources

arXiv2025

From Data Creator to Data Reuser: Distance Matters

Sharing research data is necessary, but not sufficient, for data reuse. Open science policies focus more heavily on data sharing than on reuse, yet both are complex, labor-intensive, expensive, and require infrastructure investments by multiple stakeholders. The value of data reuse lies in relationships between creators and reusers. By addressing knowledge exchange, rather than mere transactions between stakeholders, investments in data management and knowledge infrastructures can be made more wisely. Drawing upon empirical studies of data sharing and reuse, we develop the metaphor of distance between data creator and data reuser, identifying six dimensions of distance that influence the ability to transfer knowledge effectively: domain, methods, collaboration, curation, purposes, and time and temporality. We explore how social and socio-technical aspects of these dimensions may decrease -- or increase -- distances to be traversed between creators and reusers. Our theoretical framing of the distance between data creators and prospective reusers leads to recommendations to four categories of stakeholders on how to make data sharing and reuse more effective: data creators, data reusers, data archivists, and funding agencies. 'It takes a village' to share research data -- and a village to reuse data. Our aim is to provoke new research questions, new research, and new investments in effective and efficient circulation of research data; and to identify criteria for investments at each stage of data and research life cycles.

cs.HC↗

arXiv2025

A Benchmark for the Detection of Metalinguistic Disagreements between LLMs and Knowledge Graphs

Evaluating large language models (LLMs) for tasks like fact extraction in support of knowledge graph construction frequently involves computing accuracy metrics using a ground truth benchmark based on a knowledge graph (KG). These evaluations assume that errors represent factual disagreements. However, human discourse frequently features metalinguistic disagreement, where agents differ not on facts but on the meaning of the language used to express them. Given the complexity of natural language processing and generation using LLMs, we ask: do metalinguistic disagreements occur between LLMs and KGs? Based on an investigation using the T-REx knowledge alignment dataset, we hypothesize that metalinguistic disagreement does in fact occur between LLMs and KGs, with potential relevance for the practice of knowledge graph engineering. We propose a benchmark for evaluating the detection of factual and metalinguistic disagreements between LLMs and KGs. An initial proof of concept of such a benchmark is available on Github.

cs.CL↗

arXiv2024

Evaluating Class Membership Relations in Knowledge Graphs using Large Language Models

A backbone of knowledge graphs are their class membership relations, which assign entities to a given class. As part of the knowledge engineering process, we propose a new method for evaluating the quality of these relations by processing descriptions of a given entity and class using a zero-shot chain-of-thought classifier that uses a natural language intensional definition of a class. We evaluate the method using two publicly available knowledge graphs, Wikidata and CaLiGraph, and 7 large language models. Using the gpt-4-0125-preview large language model, the method's classification performance achieves a macro-averaged F1-score of 0.830 on data from Wikidata and 0.893 on data from CaLiGraph. Moreover, a manual analysis of the classification errors shows that 40.9% of errors were due to the knowledge graphs, with 16.0% due to missing relations and 24.9% due to incorrectly asserted relations. These results show how large language models can assist knowledge engineers in the process of knowledge graph refinement. The code and data are available on Github.

cs.CL↗