Sotabase

Career

· Research Scientist, University of Oxford, OATML2024–
· PhD researcher, University of Oxford

Publications (28)

Detecting hallucinations in large language models using semantic entropy
Nature · 2024
879
cited
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Neural Information Processing Systems · 2021
160
cited
Global green hydrogen-based steel opportunities surrounding high quality renewable energy and iron ore deposits
Nature Communications · 2023
146
cited
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
arXiv.org · 2024
131
cited
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Neural Information Processing Systems · 2024
99
cited
Structured Object-Aware Physics Prediction for Video Modeling and Planning
International Conference on Learning Representations · 2019
73
cited
Active Testing: Sample-Efficient Model Evaluation
International Conference on Machine Learning · 2021
72
cited
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
International Conference on Learning Representations · 2023
55
cited
Estimating the Hallucination Rate of Generative AI
Neural Information Processing Systems · 2024
28
cited
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Neural Information Processing Systems · 2022
27
cited
In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
arXiv.org · 2023
27
cited
CWM: An Open-Weights LLM for Research on Code Generation with World Models
arXiv.org · 2025
26
cited
Rethinking Aleatoric and Epistemic Uncertainty
International Conference on Machine Learning · 2024
19
cited
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Neural Information Processing Systems · 2023
18
cited
Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Trans. Mach. Learn. Res. · 2022
12
cited
Klassifikation
Wie Maschinen lernen · 2019
7
cited
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy
arXiv.org · 2024
6
cited
Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation
Conference on Empirical Methods in Natural Language Processing · 2025
5
cited
Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy
The Lancet Obstetrics, Gynaecology, & Women's Health · 2025
4
cited
Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling
arXiv.org · 2022
3
cited
Sotabase