arXiv subjects

Elena Simperl

Publications and source records attributed to Elena Simperl.

At least 37 records · Page 2Linked to original sources

arXiv2024

Methods to Assess the UK Government's Current Role as a Data Provider for AI

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.

cs.CY↗

arXiv2024

Croissant: A Metadata Format for ML-Ready Datasets

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 creates a shared representation across ML tools, frameworks, and platforms. Croissant makes datasets more discoverable, portable, and interoperable, thereby addressing significant challenges in ML data management. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, enabling easy loading into the most commonly-used ML frameworks, regardless of where the data is stored. Our initial evaluation by human raters shows that Croissant metadata is readable, understandable, complete, yet concise.

cs.LG↗

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

AI data transparency: an exploration through the lens of AI incidents

Knowing more about the data used to build AI systems is critical for allowing different stakeholders to play their part in ensuring responsible and appropriate deployment and use. Meanwhile, a 2023 report shows that data transparency lags significantly behind other areas of AI transparency in popular foundation models. In this research, we sought to build on these findings, exploring the status of public documentation about data practices within AI systems generating public concern. Our findings demonstrate that low data transparency persists across a wide range of systems, and further that issues of transparency and explainability at model- and system- level create barriers for investigating data transparency information to address public concerns about AI systems. We highlight a need to develop systematic ways of monitoring AI data transparency that account for the diversity of AI system types, and for such efforts to build on further understanding of the needs of those both supplying and using data transparency information.

cs.CY↗

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↗

arXiv2024

A Standardized Machine-readable Dataset Documentation Format for Responsible AI

Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croissant-RAI, a machine-readable metadata format designed to enhance the discoverability, interoperability, and trustworthiness of AI datasets. Croissant-RAI extends the Croissant metadata format and builds upon existing responsible AI (RAI) documentation frameworks, offering a standardized set of attributes and practices to facilitate community-wide adoption. Leveraging established web-publishing practices, such as Schema.org, Croissant-RAI enables dataset users to easily find and utilize RAI metadata regardless of the platform on which the datasets are published. Furthermore, it is seamlessly integrated into major data search engines, repositories, and machine learning frameworks, streamlining the reading and writing of responsible AI metadata within practitioners' existing workflows. Croissant-RAI was developed through a community-led effort. It has been designed to be adaptable to evolving documentation requirements and is supported by a Python library and a visual editor.

cs.IR↗

arXiv2024

Exploring the Impact of ChatGPT on Wikipedia Engagement

Wikipedia is one of the most popular websites in the world, serving as a major source of information and learning resource for millions of users worldwide. While motivations for its usage vary, prior research suggests shallow information gathering -- looking up facts and information or answering questions -- dominates over more in-depth usage. On the 22nd of November 2022, ChatGPT was released to the public and has quickly become a popular source of information, serving as an effective question-answering and knowledge gathering resource. Early indications have suggested that it may be drawing users away from traditional question answering services such as Stack Overflow, raising the question of how it may have impacted Wikipedia. In this paper, we explore Wikipedia user metrics across four areas: page views, unique visitor numbers, edit counts and editor numbers within twelve language instances of Wikipedia. We perform pairwise comparisons of these metrics before and after the release of ChatGPT and implement a panel regression model to observe and quantify longer-term trends. We find no evidence of a fall in engagement across any of the four metrics, instead observing that page views and visitor numbers increased in the period following ChatGPT's launch. However, we observe a lower increase in languages where ChatGPT was available than in languages where it was not, which may suggest ChatGPT's availability limited growth in those languages. Our results contribute to the understanding of how emerging generative AI tools are disrupting the Web ecosystem.

cs.HC↗

arXiv2024

ChartCheck: Explainable Fact-Checking over Real-World Chart Images

Whilst fact verification has attracted substantial interest in the natural language processing community, verifying misinforming statements against data visualizations such as charts has so far been overlooked. Charts are commonly used in the real-world to summarize and communicate key information, but they can also be easily misused to spread misinformation and promote certain agendas. In this paper, we introduce ChartCheck, a novel, large-scale dataset for explainable fact-checking against real-world charts, consisting of 1.7k charts and 10.5k human-written claims and explanations. We systematically evaluate ChartCheck using vision-language and chart-to-table models, and propose a baseline to the community. Finally, we study chart reasoning types and visual attributes that pose a challenge to these models

cs.CL↗

arXiv2024

A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation

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.

cs.CL↗

arXiv2024

Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs

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.

cs.CL↗

arXiv2023

Prompting Datasets: Data Discovery with Conversational Agents

Can large language models assist in data discovery? Data discovery predominantly happens via search on a data portal or the web, followed by assessment of the dataset to ensure it is fit for the intended purpose. The ability of conversational generative AI (CGAI) to support recommendations with reasoning implies it can suggest datasets to users, explain why it has done so, and provide information akin to documentation regarding the dataset in order to support a use decision. We hold 3 workshops with data users and find that, despite limitations around web capabilities, CGAIs are able to suggest relevant datasets and provide many of the required sensemaking activities, as well as support dataset analysis and manipulation. However, CGAIs may also suggest fictional datasets, and perform inaccurate analysis. We identify emerging practices in data discovery and present a model of these to inform future research directions and data prompt design.

cs.HC↗

arXiv2023

Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data

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.

cs.CL↗

arXiv2023

Multimodal Automated Fact-Checking: A Survey

Misinformation is often conveyed in multiple modalities, e.g. a miscaptioned image. Multimodal misinformation is perceived as more credible by humans, and spreads faster than its text-only counterparts. While an increasing body of research investigates automated fact-checking (AFC), previous surveys mostly focus on text. In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation. Furthermore, we discuss related terms used in different communities and map them to our framework. We focus on four modalities prevalent in real-world fact-checking: text, image, audio, and video. We survey benchmarks and models, and discuss limitations and promising directions for future research

cs.CL↗

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↗

arXiv2023

Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking

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.

cs.CL↗

arXiv2022

Exploring and Eliciting Needs and Preferences from Editors for Wikidata Recommendations

Wikidata is an open knowledge graph created, managed, and maintained collaboratively by a global community of volunteers. As it continues to grow, it faces substantial editor engagement challenges, including acquiring new editors to tackle an increasing workload and retaining existing editors. Experiences from other online communities and peer-production systems, including Wikipedia, suggest that recommending tasks to editors could help with both. Our aim with this paper is to elicit the user requirements for a Wikidata recommendations system. We conduct a mixed-methods study with a thematic analysis of in-depth interviews with 31 Wikidata editors and three Wikimedia managers, complemented by a quantitative analysis of edit records of 3,740 Wikidata editors. The insights gained from the study help us outline design requirements for the Wikidata recommender system. We conclude with a discussion of the implications of this work and directions for future work.

cs.HC↗

arXiv2022

ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sources

Knowledge Graphs are repositories of information that gather data from a multitude of domains and sources in the form of semantic triples, serving as a source of structured data for various crucial applications in the modern web landscape, from Wikipedia infoboxes to search engines. Such graphs mainly serve as secondary sources of information and depend on well-documented and verifiable provenance to ensure their trustworthiness and usability. However, their ability to systematically assess and assure the quality of this provenance, most crucially whether it properly supports the graph's information, relies mainly on manual processes that do not scale with size. ProVe aims at remedying this, consisting of a pipelined approach that automatically verifies whether a Knowledge Graph triple is supported by text extracted from its documented provenance. ProVe is intended to assist information curators and consists of four main steps involving rule-based methods and machine learning models: text extraction, triple verbalisation, sentence selection, and claim verification. ProVe is evaluated on a Wikidata dataset, achieving promising results overall and excellent performance on the binary classification task of detecting support from provenance, with 87.5% accuracy and 82.9% F1-macro on text-rich sources. The evaluation data and scripts used in this paper are available on GitHub and Figshare.

cs.CL↗

arXiv2022

A Decade of Knowledge Graphs in Natural Language Processing: A Survey

In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.

cs.CL↗