Research Areas & Discussion Topics

Our talks, reading groups, tutorials, and discussions cover cutting-edge research including:

Large Language Models & Reasoning

Exploring the latest developments in LLMs, multi-step reasoning, chain-of-thought prompting, and emergent capabilities in foundation models.

Evaluation & Benchmarking

Developing robust evaluation frameworks, synthetic data generation techniques, and novel benchmarks for assessing model performance and capabilities.

Trust & Verification

Advancing fact-checking systems, rumour detection, misinformation analysis, and building trustworthy AI systems for information verification.

Social Sciences Applications

Applying cutting-edge NLP techniques to understand social phenomena, cultural patterns, and human behavior through textual data analysis.

Prompt Engineering & Alignment

Investigating prompt design strategies, in-context learning, few-shot techniques, and AI alignment methods for better human-AI interaction.