Advancing AI Systems
Robust, Trustwory Solutions

As leading AI researchers, we push the boundaries of Machine Learning, NLP, and Generative AI. Our work advances the state of AI, focusing on mitigating hallucinations, enhancing model accuracy, and ensuring data security across diverse industries.

Using Natural Language Explanations
to Improve Robustness of In-context Learning

AI models are improving in decision-making, but their reliability against adversarial inputs remains a challenge. Our research shows how integrating human-like natural language explanations can strengthen model robustness, delivering more accurate results across complex tasks.

Advancing AI Systems
Robust, Trustwory Solutions

Using Natural Language Explanations
to Improve Robustness of In-context Learning

Selected Publications

Steering Knowledge Selection Behaviours in LLMs

Low-rank lottery tickets

Robust low-rank training via approximate orthonormal constraints

Are We Done with MMLU?

Enhancing AI Model Robustness with Natural Language Explanations

Let's solve your impossible problem

Advancing AI Systems Robust, Trustwory Solutions

Using Natural Language Explanations to Improve Robustness of In-context Learning

Selected Publications

Steering Knowledge Selection Behaviours in LLMs

Low-rank lottery tickets

Robust low-rank training via approximate orthonormal constraints

Are We Done with MMLU?

Enhancing AI Model Robustness with Natural Language Explanations

Let's solve your impossible problem

Advancing AI Systems
Robust, Trustwory Solutions

Using Natural Language Explanations
to Improve Robustness of In-context Learning