Explanipedia

Exploring the role of large language models in the scientific method: from hypothesis to discovery Open

Yanbo Zhang, Sumeer Ahmad Khan, A. K. M. Firoj Mahmud, Huck Yang, Alexander Lavin , et al. · 2025

We review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to s…

Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery Open

Yanbo Zhang, A. K. M. Firoj Mahmud, Huck Yang, Alexander Lavin, Michael Levin , et al. · 2025

With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scientific method. LLMs are now involved in experimental design…

Prolonged Exposure to Deoxycholic Acid Impairs Intestinal Barrier Function in Caco-2 Cell Model Open

Sema Oncel, Alan Bundy, Huawei Zeng · 2025

Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering Open

Nick Ferguson, Liane Guillou, Alan Bundy, Kwabena Nuamah · 2025

Large Language Models (LLMs) excel in natural language tasks but still face challenges in Question Answering (QA) tasks requiring complex, multi-step reasoning. We outline the types of reasoning required in some of these tasks, and reframe…

Assessing the Quality of a Knowledge Graph via Link Prediction Tasks Open

Ruiqi Zhu, Alan Bundy, Jeff Z. Pan, Kwabena Nuamah, Fangrong Wang , et al. · 2023

Knowledge Graph (KG) Construction is the prerequisite for all other KG research and applications. Researchers and engineers have proposed various approaches to build KGs for their use cases. However, how can we know whether our constructed…

The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence Open

Héctor Zenil, Jesper Tegnér, Felipe S. Abrahão, Alexander Lavin, Vipin Kumar , et al. · 2023

Recent advances in machine learning and AI, including Generative AI and LLMs, are disrupting technological innovation, product development, and society as a whole. AI's contribution to technology can come from multiple approaches that requ…

Representational change is integral to reasoning Open

Alan Bundy, Xue Li · 2023

Reasoning is the derivation of new knowledge from old. The reasoner must represent both the old and new knowledge. This representation will change as reasoning proceeds. This change will not just be the addition of the new knowledge. We cl…

Introduction to ‘Cognitive artificial intelligence’ Open

Alan Bundy, Nick Chater, Stephen Muggleton · 2023

There is an increasing excitement concerning the potential of artificial intelligence to both transform human society and to understand cognition in humans and other animals. This meeting addressed the leading edge of research intersection…

ALIST: Associative Logic for Inference, Storage and Transfer. A Lingua Franca for Inference on the Web Open

Kwabena Nuamah, Alan Bundy · 2023

Recent developments in support for constructing knowledge graphs have led to a rapid rise in their creation both on the Web and within organisations. Added to existing sources of data, including relational databases, APIs, etc., there is a…

TREAT: Automated Construction and Maintenance of Probabilistic Knowledge Bases from Logs (Extended Abstract) Open

Ruiqi Zhu, Xue Li, Fangrong Wang, Alan Bundy, Jeff Z. Pan , et al. · 2023

Knowledge bases (KBs) are ideal vehicles for tackling many challenges, such as Query Answering, Root Cause Analysis. Given that the world is changing over time, previously acquired knowledge can become outdated. Thus, we need methods to up…

ABC in Root Cause Analysis: Discovering Missing Information and Repairing System Failures Open

Xue Li, Alan Bundy, Ruiqi Zhu, Fangrong Wang, Stefano Mauceri , et al. · 2023

Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA system Open

Nick Ferguson, Liane Guillou, Kwabena Nuamah, Alan Bundy · 2022

We present a study into the ability of paraphrase generation methods to increase the variety of natural language questions that the FRANK Question Answering system can answer. We first evaluate paraphrase generation methods on the LC-QuAD …

Signature Entrenchment and Conceptual Changes in Automated Theory Repair Open

Xue Li, Alan Bundy, Eugene Philalithis · 2022

Human beliefs change, but so do the concepts that underpin them. The recent Abduction, Belief Revision and Conceptual Change (ABC) repair system combines several methods from automated theory repair to expand, contract, or reform logical s…

Unified Decomposition-Aggregation (UDA) Rules: Dynamic, Schematic, Novel Axioms Open

Alan Bundy, Kwabena Nuamah · 2022

We introduce Unified Decomposition-Aggregation (UDA) Rules. They are a family of axiom schemata that are instantiated at run-time to add new axioms to a logical theory. These new axioms are implications, whose preconditions will be constru…

Table of Contents Open

Alan Bundy, Kwabena Nuamah · 2021

The Use of Max-Sat for Optimal Choice of Automated Theory Repairs Open

Marius Urbonas, Alan Bundy, Juan Casanova, Xue Li · 2020

Explainable Inference in the FRANK Query Answering System Open

Kwabena Nuamah, Alan Bundy · 2020

The demand for insights into how artificial intelligent systems work is rapidly growing. This has arisen as AI systems are being integrated into almost every aspect of our lives from finance to health, security and our social lives. Curren…

Automating Event-B invariant proofs by rippling and proof patching Open

Yuhui Lin, Alan Bundy, Gudmund Grov, Ewen Maclean · 2019

The use of formal method techniques can contribute to the production of more reliable and dependable systems. However, a common bottleneck for industrial adoption of such techniques is the needs for interactive proofs. We use a popular for…

A Common Type of Rigorous Proof that Resists Hilbert’s Programme Open

Alan Bundy, Mateja Jamnik · 2019

ABC Repair System for Datalog-like Theories Open

Xue Li, Alan Bundy, Alan Smaill · 2018

This paper aims to develop a domain-independent system for repairing faulty Datalog-like theories by combining three existing techniques: abduction, belief revision and conceptual change.Accordingly, the proposed system is named the ABC re…

Smart machines are not a threat to humanity Open

Alan Bundy · 2017

Worrying about machines that are too smart distracts us from the real and present threat from machines that are too dumb.

Automating Change of Representation for Proofs in Discrete Mathematics (Extended Version) Open

Daniel Raggi, Alan Bundy, Gudmund Grov, Alison Pease · 2016

Representation determines how we can reason about a specific problem. Sometimes one representation helps us to find a proof more easily than others. Most current automated reasoning tools focus on reasoning within one representation. There…

Getting to know your Card Open

Andriana Gkaniatsou, Fiona McNeill, Alan Bundy, Graham Steel, Riccardo Focardi , et al. · 2015

Smart-cards are considered to be one of the most secure, tamper-resistant, and trusted devices for implementing confidential operations, such as authentication, key management, encryption and decryption for financial, communication, securi…

The Theory behind Theory Mine Open

Alan Bundy, Flaminia Cavallo, Lucas Dixon, Moa Johansson, Roy McCasland · 2015

The Theory Mine novelty gift company sells the rights to name novel mathematical theorems. The technology is made up of a pipeline of four computer systems that generates recursive theories, then speculates conjectures in those theories an…

Automating change of representation for proofs in discrete mathematics Open

Daniel Raggi, Alan Bundy, Gudmund Grov, Alison Pease · 2015

Representation determines how we can reason about a specific problem. Sometimes one representation helps us find a proof more easily than others. Most current automated reasoning tools focus on reasoning within one representation. There is…

Solving guesstimation problems using the Semantic Web: Four lessons from an application Open

Alan Bundy, Gintautas Sasnauskas, Michael Chan · 2015

We draw on our experience of implementing a semi-automated guesstimation application of the Semantic Web, gort, to draw four lessons, which we claim are of general applicability.These are:1. Inference can unleash the Semantic Web: The full…

Alan Bundy YOU? Author Swipe