Filter

  • Teaching Large Language Models To Perform Complex Reasoning

    Project ID: STAI-CDT-2023-IC-9
    Themes: AI Planning, Logic
    Supervisor: Dr Marek Rei

    Large language models have become the main backbone of most state-of-the-art NLP systems. By pre-training on very large datasets with unsupervised objectives, these models are able to learn good representations for language...

    Read more

  • Ensuring Trustworthy AI through Verification and Validation in ML Implementations: Compilers and Libraries

    Project ID: STAI-CDT-2023-KCL-30
    Themes: Logic, Verification
    Supervisor: Dr Hector Menendez Benito, Dr Karine Even Mendoza

    The issue of machine learning trust is a pressing concern that has brought together multiple communities to tackle it. With the increasing use of tools such as ChatGPT and the identification of fairness issues, ensuring the...

    Read more

  • Reasoning about Stochastic Games of Imperfect Information

    Project ID: STAI-CDT-2023-IC-6
    Themes: Logic, Verification
    Supervisor: Dr Francesco Belardinelli

    In many games the outcome of the players’ actions is given stochastically rather than deterministically, e.g., in card games, board games with dice (Risk!), etc.However, the literature of logic-based languages for...

    Read more

  • Multi-Task Reinforcement Learning with Imagination-based Agents

    Project ID: STAI-CDT-2023-IC-5
    Themes: Logic, Verification
    Supervisor: Dr Francesco Belardinelli

    Deep Reinforcement Learning (DRL) has proved to be a powerful technique that allows autonomous agents to learn optimal behaviours (aka policies) in unknown and complex environments through models of rewards and...

    Read more

  • Neurosymbolic approaches to causal representation learning

    Project ID: STAI-CDT-2023-KCL-26
    Themes: Logic, Verification
    Supervisor: David Watson

    Causal reasoning is essential to decision-making in real-world problems. However, observational data is rarely sufficient to infer causal relationships or estimate treatment effects due to confounding signals. Pearl (2009)...

    Read more

  • Verification of Matching Algorithms for Social Welfare

    Project ID: STAI-CDT-2023-KCL-19
    Themes: Logic, Verification
    Supervisor: Mohammad Abdulaziz

    Matching is a fundamental problem in combinatorial optimisation with multiple applications in AI, like in belief propagation [10], multi-agent resource allocation algorithms [6], and constraint solving [16], and in...

    Read more

  • Extracting interpretable symbolic representations from neural networks using information theory and causal abstraction

    Project ID: STAI-CDT-2023-IC-4
    Themes: Logic, Norms, Reasoning
    Supervisor: Pedro Mediano

    Neurosymbolic systems seek to combine the strengths of two major classes of AI algorithms: neural networks, able to recognise patterns in unstructured data, and logic-based systems, capable of powerful reasoning. One of the...

    Read more

  • Improving Robustness of Pre-Trained Language Models

    Project ID: STAI-CDT-2023-KCL-25
    Themes: Logic, Norms, Reasoning
    Supervisor: Yulan He

    Recent efforts to Natural Language Understanding (NLU) have been largely exemplified in tasks such as natural language inference, reading comprehension and question answering. We have witnessed the shift of paradigms in NLP...

    Read more

  • Causal Temporal Logic

    Project ID: STAI-CDT-2023-KCL-18
    Themes: Logic
    Supervisor: Nicola Paoletti

    Temporal logic (TL) is arguably the primary language for formal specification and reasoning about system correctness and safety. They enable the specification and verification of properties such as “will the agent...

    Read more

  • Explanations of Medical Images

    Project ID: STAI-CDT-2023-KCL-24
    Themes: Logic, Verification
    Supervisor: Hana Chockler

    We developed a framework for causal explanations of image classifiers based on the principled approach of actual causality [1] and responsibility [2], the latter pioneered by Dr Chockler. Our framework already resulted in a...

    Read more

  • Multiple Explanations of AI image classifiers

    Project ID: STAI-CDT-2023-KCL-23
    Themes: Logic, Verification
    Supervisor: Hana Chockler

    We developed a framework for causal explanations of image classifiers based on the principled approach of actual causality [1] and responsibility [2], the latter pioneered by Dr Chockler. Our framework already resulted in a...

    Read more

  • Integrating Sub-symbolic and Symbolic Reasoning for Value Alignment

    Project ID: STAI-CDT-2023-KCL-22
    Themes: Logic
    Supervisor: Sanjay Modgil, Odinaldo Rodrigues

    An important long-term concern regarding the ethical impact of AI is the so called ‘value alignment problem’; that is, how to ensure that the decisions of autonomous AIs are aligned with human values. Addressing...

    Read more