large language models

Oil market narratives and their economic effect

This thesis investigates the economic importance of oil narratives in affecting financial markets over the period 1984 to 2018. Over this period oil narratives are of particular interest due to geopolitical events that are communicated through media and influencing the oil market. Over 100,000 oil-related articles from...

Optimisation of biopsy practice to facilitate timely diagnosis and management of kidney disease

Background: A kidney biopsy is an invasive investigation to diagnose intrinsic forms of kidney disease such as glomerulonephritis (GN). There is a rare risk of significant complications including bleeding requiring transfusion, embolisation or death. Previous literature is limited in terms of the patient experience and...

AI for public good: reorientating fairness, accountability and uncertainty in public sector governance

AI is no longer confined to laboratories or private enterprise; it is increasingly embedded within the institutions of public governance. From predictive systems in welfare and justice to large language models shaping policy processes, AI now mediates decisions that affect lives and democratic legitimacy alike. Yet the...

Integrating online cooperative learning into the English as a foreign language writing curriculum: a modelling trial

Online learning has been reported to be increasingly used within Chinese higher education. The rapid expansion has created a problem that it’s difficult to carry out real-time learner interaction among a great number of students. The pure online instruction made the existing problems in university EFL teaching even wor...

Reproducible synthetic clinical letters for seizure frequency information extraction

CONCUR: Benchmarking LLMs for Concurrent Code Generation

Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluate the code generation capabilities of LLMs. However, existing benchmarks focus primarily on sequential code, lacking the ab...

Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation

Software testing is a critical, yet resource-intensive phase of the software development lifecycle. Search-based approaches typically achieve high coverage but produce tests with low readability, whereas large language model (LLM)-based methods generate more human-readable tests but often suffer from low coverage and c...

Lookahead-Then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars

Diffusion Large Language Models (dLLMs) have demonstrated promising capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as probabilistic models, they still struggle to generate syntactically valid outputs reliably. A...

Better Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code Completion

Repository-level code completion remains challenging for large language models (LLMs), as it requires reasoning over cross-file dependencies while under limited context windows. To address this challenge, prior work has adopted Retrieval-Augmented Generation (RAG) frameworks based on semantic indexing or structure-awar...

On the Evaluation of Large Language Models in Unit Test Evolution (Experience Paper)

Large language models (LLMs) have recently shown promising potential in automating unit test evolution for evolving software systems. However, the effectiveness of LLMs in unit test evolution remains insufficiently understood, particularly with respect to prompt design choices, in-context learning (ICL) strategies, and...

Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its potential impact on model performance eval...

Is “Knowing It’s Malicious” Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with concrete code evidence, a requirement that traditional signature-based methods and learning-based XAI often fail to satisfy in a human-in...