arXiv subjects

Andrew Reeson

Publications and source records attributed to Andrew Reeson.

5 recordsLinked to original sources

arXiv2026

An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations

Despite extensive research, Large Language Models continue to hallucinate when generating code, particularly when using libraries. On NL-to-code benchmarks that require library use, we find that LLMs generate code that uses non-existent library features in 8.1-40% of responses. One intuitive approach for detection and mitigation of hallucinations is static analysis. In this paper, we analyse the potential of static analysis tools, both in terms of what they can solve and what they cannot. We find that static analysis tools can detect 16-70% of all errors, and 14-85% of library hallucinations, with performance varying by LLM and dataset. Through manual analysis, we identify cases a static method could not plausibly catch, which gives an upper bound on their potential from 48.5% to 77%. Overall, we show that static analysis methods are cheap method for addressing some forms of hallucination, and we quantify how far short of solving the problem they will always be.

cs.CL↗

arXiv2025

A Qualitative Study of User Perception of M365 AI Copilot

Adopting AI copilots in professional workflows presents opportunities for enhanced productivity, efficiency, and decision making. In this paper, we present results from a six month trial of M365 Copilot conducted at our organisation in 2024. A qualitative interview study was carried out with 27 participants. The study explored user perceptions of M365 Copilot's effectiveness, productivity impact, evolving expectations, ethical concerns, and overall satisfaction. Initial enthusiasm for the tool was met with mixed post trial experiences. While some users found M365 Copilot beneficial for tasks such as email coaching, meeting summaries, and content retrieval, others reported unmet expectations in areas requiring deeper contextual understanding, reasoning, and integration with existing workflows. Ethical concerns were a recurring theme, with users highlighting issues related to data privacy, transparency, and AI bias. While M365 Copilot demonstrated value in specific operational areas, its broader impact remained constrained by usability limitations and the need for human oversight to validate AI generated outputs.

cs.CY↗

arXiv2024

Survey Insights on M365 Copilot Adoption

Australia's National Science Agency conducted a six-month trial of M365 Copilot starting in January 2024 as part of an Australian Government initiative. Three hundred licenses were distributed across CSIRO using a persona-based approach to ensure diversity of roles and attributes among participants. As a scientific research organisation with a unique operational context, our objective was to study the use of M365 Copilot on enhancing productivity, efficiency, and creativity as well as overall satisfaction and ethical considerations. This paper presents the results from two surveys, conducted before and after the trial. The results showed mixed outcomes, with participants reporting improved productivity and efficiency in structured tasks such as meeting summaries and email drafting. Gaps were identified in advanced functionalities and integration, which limited Copilot's overall effectiveness. Satisfaction levels were generally positive, but user experiences varied in certain areas. Ethical concerns, particularly around data privacy, became more pronounced post-trial. These findings highlight Copilot's potential and the need for further refinement to meet users' diverse needs.

cs.HC↗

arXiv2024

Do Text-to-Vis Benchmarks Test Real Use of Visualisations?

Large language models are able to generate code for visualisations in response to simple user requests. This is a useful application and an appealing one for NLP research because plots of data provide grounding for language. However, there are relatively few benchmarks, and those that exist may not be representative of what users do in practice. This paper investigates whether benchmarks reflect real-world use through an empirical study comparing benchmark datasets with code from public repositories. Our findings reveal a substantial gap, with evaluations not testing the same distribution of chart types, attributes, and actions as real-world examples. One dataset is representative, but requires extensive modification to become a practical end-to-end benchmark. This shows that new benchmarks are needed to support the development of systems that truly address users' visualisation needs. These observations will guide future data creation, highlighting which features hold genuine significance for users.

cs.CL↗

arXiv2020

China's First Workforce Skill Taxonomy

China is the world's second largest economy. After four decades of economic miracles, China's economy is transitioning into an advanced, knowledge-based economy. Yet, we still lack a detailed understanding of the skills that underly the Chinese labor force, and the development and spatial distribution of these skills. For example, the US standardized skill taxonomy O*NET played an important role in understanding the dynamics of manufacturing and knowledge-based work, as well as potential risks from automation and outsourcing. Here, we use Machine Learning techniques to bridge this gap, creating China's first workforce skill taxonomy, and map it to O*NET. This enables us to reveal workforce skill polarization into social-cognitive skills and sensory-physical skills, and to explore the China's regional inequality in light of workforce skills, and compare it to traditional metrics such as education. We build an online tool for the public and policy makers to explore the skill taxonomy: skills.sysu.edu.cn. We will also make the taxonomy dataset publicly available for other researchers upon publication.

econ.GN↗