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.

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.

From Data Creator to Data Reuser: Distance Matters

Sharing research data is complex, labor-intensive, expensive, and requires infrastructure investments by multiple stakeholders. Open science policies focus on data release rather than on data reuse, yet reuse is also difficult, expensive, and may never occur. Investments in data management could be made more wisely by considering who might reuse data, how, why, for what purposes, and when. Data creators cannot anticipate all possible reuses or reusers; our goal is to identify factors that may aid stakeholders in deciding how to invest in research data, how to identify potential reuses and reusers, and how to improve data exchange processes. Drawing upon empirical studies of data sharing and reuse, we develop the theoretical construct of distance between data creator and data reuser, identifying six distance dimensions that influence the ability to transfer knowledge effectively: domain, methods, collaboration, curation, purposes, and time and temporality. These dimensions are primarily social in character, with associated technical aspects that can decrease - or increase - distances between creators and reusers. We identify the order of expected influence on data reuse and ways in which the six dimensions are interdependent. 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.