Projects

Ongoing Projects

CArLA: Causal Argumentative Learning Assistant
Funded by ERC (2025-2026)

In the world of AI, understanding causation is vital, especially in fields like healthcare and finance, where decisions impact lives and economies. Current AI models often lack transparency, relying on opaque methods that make it challenging for experts to verify or contest findings. Addressing this gap, the ERC-funded CArLA project aims to revolutionise causal discovery–the task of uncovering causal relationships from data. Building on robust methodologies and explainable AI (XAI) principles from the ERC ADIX project, CArLA’s platform will make causal discovery more transparent, interactive and contestable. The project will develop demonstrators in healthcare and finance, enabling experts to influence and verify AI-generated insights, thus fostering a more reliable, human-aligned AI approach for high-stakes decision-making.

ADIX: Argumentation-based Deep Interactive eXplanations
Funded by ERC (2021-2026)

ADIX strives towards a radical re-thinking of explainable AI that can work in synergy with humans within a human-centred but AI-supported society. It aims to define a novel scientific paradigm of deep, interactive explanations that can be deployed alongside a variety of data-centric AI methods to explain their outputs by providing justifications in their support. These can be progressively questioned by humans and the outputs of the AI methods refined as a result of human feedback, within explanatory exchanges between humans and machines. This paradigm is being realised using computational argumentation as the underpinning, unifying theoretical foundation.

Explainable AI by Learning Argumentation Frameworks
Funded by Royal Society

This project supports a collaboration with Maurizio Proietti and Emanuele de Angelis at CNR to study the automatic learning of Assumption-based Argumentation (ABA) frameworks from data.

Past Projects

INDICATE: AI-enabled data curation, quality and fact-checking for medical documents
Funded by UKRI (2023-2025)

The project uses AI for real time analysis of healthcare infodemics to autonomously create clinical guidance and identify misinformation.

Argumentation-based Interactive Explainable AI
Funded by Royal Academy of Engineering/JP Morgan (2022-2024)

The project aims to deliver machines, powered by a variety of AI methods, which can engage with humans in two-way explanatory dialogues. The machines will explain their recommendations and humans will question their explanations and provide feedback. Such explanations can be drawn to engage humans and make them trust the methods' outputs.

ROAD2H
Funded by EPSRC (2017-2020)

ROAD2H is a collaborative project with Imperial College London, King’s College London, University of Serbia and China National Health Development Research Center. The project aims to develop novel Learning Health System techniques to facilitate Universal Health Coverage (UHC) in low- and middle-income countries.

Analysing the Passage of UK Parliament Bills 2017

This is a project in collaboration with Thomson Reuters, Data Science Institute and Imperial College Business School. Kristijonas Cyras has driven the development of both methodology and a working system to explain primary legislation outcomes -- See Argumentative arbitrated disputes.

TRaDAr
Funded by EPSRC

TRaDAr aims at providing methods and prototype systems for various kinds of argumentation-based (individual and collaborative) decision-making that generate automatically transparent, rational decisions, while developing case studies in smart electricity and e-health to inform and validate methods and systems.

DesMOLD
Funded by the European Union's Seventh Framework Programme (FP/2007-2013)

The strategic objective of the Des-MOLD project is to reduce the cost of injection-moulding production by developing and validating a set of knowledge-based tools specifically oriented to mould makers and plastic injection companies, which will reduce the need for mock-ups of moulds, and several try-and-error trials to calibrate process control variables.

Agreement Technologies
Funded by COST (2008-2012)

The Agreement Technologies Action aims at coordinating national efforts on a new paradigm for next generation distributed systems, based on the concept of agreement between computational agents.

ARGUGRID
Funded by the European Union's Sixth Framework Programme (2006-2009)

The ArguGRID project aims at supporting service selection and composition in distributed environments, including the Grid and Service-oriented architectures, by means of argumentative agents, an agent environment, a service-composition environment, Peer-to-Peer technology and Grid middleware.