Sotabase

Career

· Researcher, UCL DARK Lab2026–

Publications (15)

Debating with More Persuasive LLMs Leads to More Truthful Answers
International Conference on Machine Learning · 2024
208
cited
A Benchmark for Systematic Generalization in Grounded Language Understanding
Neural Information Processing Systems · 2020
152
cited
The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
2022
60
cited
Command A: An Enterprise-Ready Large Language Model
arXiv.org · 2025
37
cited
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
arXiv.org · 2024
26
cited
Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
arXiv.org · 2024
22
cited
Investigating Non-Transitivity in LLM-as-a-Judge
International Conference on Machine Learning · 2025
20
cited
Improving Systematic Generalization Through Modularity and Augmentation
Annual Meeting of the Cognitive Science Society · 2022
18
cited
Insertion-Deletion Transformer
arXiv.org · 2020
10
cited
Programming by Backprop: LLMs Acquire Reusable Algorithmic Abstractions During Code Training
arXiv.org · 2025
2
cited
Do LLMs selectively encode the goal of an agent’s reach?
1
cited
InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models with Human Feedback
Conference on Empirical Methods in Natural Language Processing · 2025
Sotabase