AIConfPaper
← Search

Murray Shanahan

14 accepted papers

2026

Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models

Lujain Ibrahim, Canfer Akbulut, Rasmi Elasmar, Charvi Rastogi, Minsuk Kahng, Meredith Ringel Morris +4
ICLR 2026poster

The tendency of users to anthropomorphise large language models (LLMs) is of growing societal interest. Here, we present AnthroBench: a novel empirical method and tool for evaluating anthropomorphic LLM behaviours in realistic settings. Our work introduces three key advances; first, we develop a mul…

Cited by 0Source ↗code ↗Scholar ↗
2025

Learning dynamics in linear recurrent neural networks

Alexandra Maria Proca, Clémentine Carla Juliette Dominé, Murray Shanahan, Pedro A. M. Mediano
ICML 2025oral

Recurrent neural networks (RNNs) are powerful models used widely in both machine learning and neuroscience to learn tasks with temporal dependencies and to model neural dynamics. However, despite significant advancements in the theory of RNNs, there is still limited understanding of their learning p…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Schema-learning and rebinding as mechanisms of in-context learning and emergence

Sivaramakrishnan Swaminathan, Antoine Dedieu, Rajkumar Vasudeva Raju, Murray Shanahan, Miguel Lazaro-Gredilla, Dileep George
NeurIPS 2023spotlight

In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs). Yet the mechanisms that underlie it are poorly understood. In this paper, we demonstrate that comparable ICL capabilities can be acquired by an a…

Cited by 20Source ↗PDF ↗Scholar ↗
2023

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Antonia Creswell, Murray Shanahan, Irina Higgins
ICLR 2023top-5%

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation of LLMs on 46 tasks that probe different aspects of logical…

Cited by 384Source ↗PDF ↗Scholar ↗
2022

In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

Borja G. León, Murray Shanahan, Francesco Belardinelli
ICLR 2022poster

We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the agent's neural architecture is a key feature when DRL age…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2021

Unsupervised Object-Based Transition Models For 3D Partially Observable Environments

Antonia Creswell, Rishabh Kabra, Christopher P. Burgess, Murray Shanahan
NeurIPS 2021poster

We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames. The model is trained end-to-end without superv…

Cited by 27Source ↗PDF ↗Scholar ↗
2020

An Explicitly Relational Neural Network Architecture

Murray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis, David Barrett, Marta Garnelo
ICML 2020poster

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introd…

Cited by 82Source ↗PDF ↗Scholar ↗
2020

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie +2
ICML 2020poster

Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what’s directly observed through sensation. Top-down signals consist of beliefs and expectations based on past experience and the current reportable short-term memory, such as how the phrase ‘peanut butter…

Cited by 83Source ↗PDF ↗code ↗Scholar ↗
2019

Deep reinforcement learning with relational inductive biases

Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin +10
ICLR 2019poster

We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability. Our architecture encodes an image as a set of vector…

Cited by 265Source ↗PDF ↗Scholar ↗
2018

Conditional Neural Processes

Marta Garnelo, Dan Rosenbaum, Christopher Maddison, Tiago Ramalho, David Saxton, Murray Shanahan +3
ICML 2018oral

Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a new function at test time. Yet, GPs are computationa…

Cited by 906Source ↗PDF ↗Scholar ↗
2018

SCAN: Learning Hierarchical Compositional Visual Concepts

Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matko Bošnjak +4
ICLR 2018poster

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through primarily unsupervised experiences and represented as abstract…

Cited by 151Source ↗PDF ↗Scholar ↗