The School of Computer Science, here at the ±¬ÁÏTV, has secured project funding from the to develop high-quality datasets aimed at making artificial intelligence systems safer, more reliable, and better aligned with the real world.
The funding, awarded through the Hub’s , supports pioneering research at the forefront of science, technology, and professional services. Within the School of Computer Science, we will use the funding to accelerate the creation of authoritative, open-source datasets, which provide a critical foundation for advancing modern and trustworthy AI systems.
Titled, ‘Multi-DocVerify: A Multimodal Evidence-Based Benchmark for Professional Contexts​’, the project is led by Dr Xingyi Song, Lecturer in Computational Media Analysis, alongside Dr Carolina Scarton, Senior Lecturer in Natural Language Processing, as co-investigator.
Multi-DocVerify benchmarks AI’s ability to learn from complex real-world documents (including charts, tables, and long texts), prioritising new evidence over training data, and will be tested via professional fact-checking scenarios. We are also collaborating on the project with and the .
The project aims to unlock new applications across sectors, including professional services, while strengthening the UK’s position in responsible AI innovation.
Dr Xingyi Song said, “We are excited to receive this award, since it allows us to tackle a critical and timely challenge in Generative AI: the processing of large, multimodal documents. While Gen AI, such as Retrieval-Augmented Generation (RAG), is being widely adopted across many industries, its performance in real-world applications remains under-evaluated.
“This award gives us the opportunity to strengthen collaborations with our industrial partners, Full Fact and AMRC, by developing and benchmarking Gen AI models in their real-world use cases, directly contributing to solving practical problems and ensuring the safety and efficiency of Gen AI deployment."
The AI Hub for Generative Models brings together leading researchers from academia and industry to develop more customisable, reliable, and trustworthy generative AI systems.
The hub is one of nine UK AI research hubs funded by the Engineering and Physical Sciences Research Council (EPSRC) as part of UKRI’s AI programme. These awards are the first made through an open funding call by the hub, which brings together experts in Generative AI from industry and academia.