Sotabase

Career

· Research Scientist, FutureHouse2025–2025
· PhD in Computer Science, University of Oxford2020–2025
· Research Intern, Mila
· Student (Previous Studies), University of Cape Town, Department of Electrical Engineering
· Assistant Lecturer, University of Cape Town, Department of Mechanical Engineering

Publications (10)

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
International Conference on Machine Learning · 2022
220
cited
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
arXiv.org · 2024
131
cited
Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation
Isprs Journal of Photogrammetry and Remote Sensing · 2021
58
cited
Prioritized training on points that are learnable, worth learning, and not yet learned
arXiv.org · 2021
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
Scaling Up Active Testing to Large Language Models
arXiv.org · 2025
1
cited
MADE: Benchmark Environments for Closed-Loop Materials Discovery
2026
The Benefits and Risks of Transductive Approaches for AI Fairness
arXiv.org · 2024
Sotabase
Muhammed Razzak | Researcher Profile | Sotabase | Sotabase