Maeve Hutchinson
PhD Candidate studying NLP and Data Visualization
City St George's, University of London
(Formerly City, University of London)
I am a third-year PhD candidate supervised by Pranava Madhyastha, Radu Jianu, and Aidan Slingsby, working in the giCentre and AI Centre.
My research spans data visualization, natural language processing, and human–AI interaction. I am interested in natural language as both a human artefact of visual analytics and a medium through which LLMs can support analytic processes. My recent projects examine the natural-language traces of analysts' behaviour, focusing on how they articulate visualization design rationale, and the development of human-grounded visualization benchmarks for multimodal LLMs. My broader goal is to contribute to grounded AI systems aligned with natural language, visual data, and human intent.
Publications
- InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations Conference on Empirical Methods in Natural Language Processing (EMNLP 2026).
- Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs IEEE Visualization and Visual Analytics (VIS 2026).
- Capturing Visualization Design Rationale IEEE Visualization and Visual Analytics (VIS 2025).
- Chart Question Answering from Real-World Analytical Narratives Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Student Research Workshop.
- Mind-Mapping Data Analysis with LLMs: From Vision to First Steps Computer Graphics & Visual Computing (CGVC), 2025.
- Foundation Model Assisted Visual Analytics: Opportunities and Challenges Computers & Graphics, 2025.
- LLM-Assisted Visual Analytics: Opportunities and Challenges Computer Graphics & Visual Computing (CGVC), 2024.
- Towards Visualisation Specifications from Multilingual Natural Language Queries using Large Language Models EuroVis 2023 – Posters.