Harry Mayne

According to our database, Harry Mayne authored at least 10 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior.

Harry Mayne, Justin Singh Kang, Dewi Gould, Kannan Ramchandran, Adam Mahdi, Noah Y. Siegel

CoRR, February, 2026

2025

Measuring what Matters: Construct Validity in Large Language Model Benchmarks.

Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner, Harry Mayne, Jan Batzner, Negar Foroutan, Chris Schmitz, Karolina Korgul, Hunar Batra, Oishi Deb, Emma Beharry, Cornelius Emde, Thomas Foster, Anna Gausen, María Grandury, Simeng Han, Valentin Hofmann, Lujain Ibrahim, Hazel Kim, Hannah Rose Kirk, Fangru Lin, Gabrielle Kaili-May Liu, Lennart Luettgau, Jabez Magomere, Jonathan Rystrøm, Anna Sotnikova, Yushi Yang, Yilun Zhao, Adel Bibi, Antoine Bosselut, Ronald Clark, Arman Cohan, Jakob N. Foerster, Yarin Gal, Scott A. Hale, Inioluwa Deborah Raji, Christopher Summerfield, Philip H. S. Torr, Cozmin Ududec, Luc Rocher, Adam Mahdi

CoRR, November, 2025

LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation.

Jude Khouja, Karolina Korgul, Simi Hellsten, Lingyi Yang, Vlad Neacsu, Harry Mayne, Ryan Kearns, Andrew M. Bean, Adam Mahdi

CoRR, March, 2025

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis.

Yushi Yang, Filip Sondej, Harry Mayne, Andrew Lee, Adam Mahdi

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations.

Harry Mayne, Ryan Othniel Kearns, Yushi Yang, Andrew M. Bean, Eoin D. Delaney, Chris Russell, Adam Mahdi

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Large language models can help boost food production, but be mindful of their risks.

Djavan De Clercq, Elias Nehring, Harry Mayne, Adam Mahdi

Frontiers Artif. Intell., 2024

Can sparse autoencoders be used to decompose and interpret steering vectors?

Harry Mayne, Yushi Yang, Adam Mahdi

CoRR, 2024

Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction.

Yushi Yang, Filip Sondej, Harry Mayne, Adam Mahdi

CoRR, 2024

Unsupervised Learning Approaches for Identifying ICU Patient Subgroups: Do Results Generalise?

Harry Mayne, Guy Parsons, Adam Mahdi

CoRR, 2024

LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages.

Andrew M. Bean, Simi Hellsten, Harry Mayne, Jabez Magomere, Ethan Chi, Ryan Chi, Scott Hale, Hannah Rose Kirk

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024