🧑‍🔬 Murray Shanahan

🏛️ Affiliations

🎓Imperial College LondonLondon · United Kingdom1981–2026 · 114 papersEducation 1981–1984 · BSc(Eng), Dept. of ComputingEmployment · Department of Computingcurrent🏢Google DeepMindLondon · United Kingdom2017–2026 · 17 papersEmployment since 2017current🎓Queen Mary University of LondonLondon · United Kingdom1996–1997 · 4 papers🏢GoogleMountain View · United States2019–2025 · 2 papers🔬Institute of PhilosophyLondon · United Kingdom2024 · 2 papers🎓School of Advanced StudyLondon · United Kingdom2024 · 2 papers🎓University of LondonLondon · United Kingdom2024 · 2 papers🎓University of CambridgeCambridge · United Kingdom1984–2022 · 2 papersEducation 1984–1987 · PhD, Computer Laboratory

🏛️DeepMind Technologies LtdLondon · United Kingdom2017Employment since 2017 · Senior Research Scientist

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Role-Play with Large Language Models (2023 · 610 citations)
   The paper addresses a conceptual problem. Chat systems built on LLMs talk so fluently that we naturally describe them with words like "knows" or "wants." Taken literally, that vocabulary misleads us into treating them as human. The authors offer no dataset or experiment. Instead they propose a framework for…
2. Faithful Reasoning Using Large Language Models (2022 · 122 citations)
   Large language models usually answer questions in a single opaque pass. Users cannot see which premises were used or check the logic, and multi-step problems suffer. Creswell and Shanahan (DeepMind) propose a forward-chaining system whose computation follows the formal definition of a valid reasoning trace.

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Role-Play with Large Language ModelsNatureMurray Shanahan, Kyle McDonell, Laria Reynolds2023 · 610 citations
2. Relational Deep Reinforcement Learning ↗arXiv (Cornell University) · no summary yetVinícius Zambaldi et al.2018 · 160 citations
3. Deep reinforcement learning with relational inductive biases ↗International Conference on Learning Representations · no summary yetVinícius Zambaldi et al.2018 · 132 citations
4. Faithful Reasoning Using Large Language ModelsarXiv:2208.14271Antonia Creswell, Murray Shanahan2022 · 122 citations
5. AlignNet: Unsupervised Entity Alignment ↗arXiv (Cornell University) · no summary yetAntonia Creswell et al.2020 · 9 citations

🤝 Co-authors here

3 co-authors with a page, the most papers together first.

• Antonia Creswell
• Kyle McDonell
• Laria Reynolds

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Nature: Nature 2023
• International Conference on Learning Representations

🔗 Cited by

Papers of our library cite their works 249 times (of the 149,439 papers whose bibliographies we read); 77 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/murray-shanahan/