UCL NLP

AI & ML interests

Language models, reasoning, robustness, question answering, evaluation, theorem proving, knowledge graphs, mechanistic interpretability, adversarial training, dynamic adversarial data collection, in-context learning, natural language explanations, safety and security, self-training, knowledge distillation, natural language processing

Recent Activity

yaolu  authored a paper 26 days ago

Multilingual Language Model Pretraining using Machine-translated Data

yaolu  authored a paper 2 months ago

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation

mbartolo  authored a paper 9 months ago

Command A: An Enterprise-Ready Large Language Model

View all activity

Team members 3