Research Projects

We study the feature flow across layers in state-space models compared to Transformers.

We incoporate external knowledge and goals for better CRS.

We generate high-quality code-mixed sentences using language models.

Translating complex scientific content into accessible language for social media platforms.

A framework integrating LLMs with external tools to enhance explainability and accuracy in table-based reasoning tasks.

We find positive use cases, but also weaknesses that need much handholding from human scientists.

We measure and enhance LLMs’ discourse understanding and reasoning faithfulness.

We benchmark and improve modern OCR systems on Southeast Asian languages.

We provide language resource for emoji composition.

This project develops a visualizer utilising attention scores to enhance transformer interpretability.