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.

Governments typically collect and steward a vast amount of high-quality data on their citizens and institutions, and the UK government is exploring how it can better publish and provision this data to the benefit of the AI landscape. However, the compositions of generative AI training corpora remain closely guarded secrets, making the planning of data sharing initiatives difficult. To address this, we devise two methods to assess UK government data usage for the training of Large Language Models (LLMs) and 'peek behind the curtain' in order to observe the UK government's current contributions as a data provider for AI. The first method, an ablation study that utilises LLM 'unlearning', seeks to examine the importance of the information held on UK government websites for LLMs and their performance in citizen query tasks. The second method, an information leakage study, seeks to ascertain whether LLMs are aware of the information held in the datasets published on the UK government's open data initiative data$.$gov$.$uk. Our findings indicate that UK government websites are important data sources for AI (heterogenously across subject matters) while data$.$gov$.$uk is not. This paper serves as a technical report, explaining in-depth the designs, mechanics, and limitations of the above experiments. It is accompanied by a complementary non-technical report on the ODI website in which we summarise the experiments and key findings, interpret them, and build a set of actionable recommendations for the UK government to take forward as it seeks to design AI policy. While we focus on UK open government data, we believe that the methods introduced in this paper present a reproducible approach to tackle the opaqueness of AI training corpora and provide organisations a framework to evaluate and maximize their contributions to AI development.

Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes datasets more discoverable, portable and interoperable, thereby addressing significant challenges in ML data management and responsible AI. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, ready to be loaded into the most popular ML frameworks.

Generating natural language text from graph-structured data is essential for conversational information seeking. Semantic triples derived from knowledge graphs can serve as a valuable source for grounding responses from conversational agents by providing a factual basis for the information they communicate. This is especially relevant in the context of large language models, which offer great potential for conversational interaction but are prone to hallucinating, omitting, or producing conflicting information. In this study, we conduct an empirical analysis of conversational large language models in generating natural language text from semantic triples. We compare four large language models of varying sizes with different prompting techniques. Through a series of benchmark experiments on the WebNLG dataset, we analyze the models' performance and identify the most common issues in the generated predictions. Our findings show that the capabilities of large language models in triple verbalization can be significantly improved through few-shot prompting, post-processing, and efficient fine-tuning techniques, particularly for smaller models that exhibit lower zero-shot performance.

Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance.

Numbers are crucial for various real-world domains such as finance, economics, and science. Thus, understanding and reasoning with numbers are essential skills for language models to solve different tasks. While different numerical benchmarks have been introduced in recent years, they are limited to specific numerical aspects mostly. In this paper, we propose a hierarchical taxonomy for numerical reasoning skills with more than ten reasoning types across four levels: representation, number sense, manipulation, and complex reasoning. We conduct a comprehensive evaluation of state-of-the-art models to identify reasoning challenges specific to them. Henceforth, we develop a diverse set of numerical probes employing a semi-automated approach. We focus on the tabular Natural Language Inference (TNLI) task as a case study and measure models' performance shifts. Our results show that no model consistently excels across all numerical reasoning types. Among the probed models, FlanT5 (few-/zero-shot) and GPT-3.5 (few-shot) demonstrate strong overall numerical reasoning skills compared to other models. Label-flipping probes indicate that models often exploit dataset artifacts to predict the correct labels.

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.

Evidence data for automated fact-checking (AFC) can be in multiple modalities such as text, tables, images, audio, or video. While there is increasing interest in using images for AFC, previous works mostly focus on detecting manipulated or fake images. We propose a novel task, chart-based fact-checking, and introduce ChartBERT as the first model for AFC against chart evidence. ChartBERT leverages textual, structural and visual information of charts to determine the veracity of textual claims. For evaluation, we create ChartFC, a new dataset of 15, 886 charts. We systematically evaluate 75 different vision-language (VL) baselines and show that ChartBERT outperforms VL models, achieving 63.8% accuracy. Our results suggest that the task is complex yet feasible, with many challenges ahead.

Wikidata is one of the most important sources of structured data on the web, built by a worldwide community of volunteers. As a secondary source, its contents must be backed by credible references; this is particularly important as Wikidata explicitly encourages editors to add claims for which there is no broad consensus, as long as they are corroborated by references. Nevertheless, despite this essential link between content and references, Wikidata's ability to systematically assess and assure the quality of its references remains limited. To this end, we carry out a mixed-methods study to determine the relevance, ease of access, and authoritativeness of Wikidata references, at scale and in different languages, using online crowdsourcing, descriptive statistics, and machine learning. Building on previous work of ours, we run a series of microtasks experiments to evaluate a large corpus of references, sampled from Wikidata triples with labels in several languages. We use a consolidated, curated version of the crowdsourced assessments to train several machine learning models to scale up the analysis to the whole of Wikidata. The findings help us ascertain the quality of references in Wikidata, and identify common challenges in defining and capturing the quality of user-generated multilingual structured data on the web. We also discuss ongoing editorial practices, which could encourage the use of higher-quality references in a more immediate way. All data and code used in the study are available on GitHub for feedback and further improvement and deployment by the research community.

We investigate the problem of generating natural language summaries from knowledge base triples. Our approach is based on a pointer-generator network, which, in addition to generating regular words from a fixed target vocabulary, is able to verbalise triples in several ways. We undertake an automatic and a human evaluation on single and open-domain summaries generation tasks. Both show that our approach significantly outperforms other data-driven baselines.