Reasoning with Machines Lab, University of Oxford

university

https://oxrml.com/

AI & ML interests

Benchmarks and Evaluation, Agentic AI for Science, AI Safety and Security, Human-AI Interaction

Recent Activity

shreyanshpadarha updated a Space 3 days ago

ammaox authored a paper 3 days ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

shreyanshpadarha authored a paper 3 days ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

View all activity

shreyanshpadarha

updated a Space 3 days ago

README

authored a paper 3 days ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 4 days ago • 55

shreyanshpadarha

authored a paper 3 days ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 4 days ago • 55

updated a Space 3 days ago

README

shreyanshpadarha

updated a dataset 3 days ago

OxRML/MADQA

Viewer • Updated 3 days ago • 3.05k • 114 • 8

shreyanshpadarha

published a Space 5 days ago

README

shreyanshpadarha

published a dataset 5 days ago

OxRML/MADQA

Viewer • Updated 3 days ago • 3.05k • 114 • 8

updated a dataset 5 days ago

OxRML/MADQA

Viewer • Updated 3 days ago • 3.05k • 114 • 8

shreyanshpadarha

authored a paper 21 days ago

Agentic Reinforcement Learning for Search is Unsafe

Paper • 2510.17431 • Published Oct 20, 2025 • 5

authored a paper 11 months ago

Clinical knowledge in LLMs does not translate to human interactions

Paper • 2504.18919 • Published Apr 26, 2025 • 26

authored a paper 11 months ago

Clinical knowledge in LLMs does not translate to human interactions

Paper • 2504.18919 • Published Apr 26, 2025 • 26

authored a paper about 1 year ago

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

Paper • 2503.02972 • Published Mar 4, 2025 • 25

authored 3 papers over 1 year ago

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

Paper • 2411.06424 • Published Nov 10, 2024 • 5

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

Paper • 2411.08790 • Published Nov 13, 2024 • 8

Evaluating the role of `Constitutions' for learning from AI feedback

Paper • 2411.10168 • Published Nov 15, 2024 • 5

authored 4 papers over 1 year ago

Evaluating the role of `Constitutions' for learning from AI feedback

Paper • 2411.10168 • Published Nov 15, 2024 • 5

The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

Paper • 2404.16019 • Published Apr 24, 2024 • 1

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

Paper • 2406.06196 • Published Jun 10, 2024

Casteist but Not Racist? Quantifying Disparities in Large Language Model Bias between India and the West

Paper • 2309.08573 • Published Sep 15, 2023