NLP and LLMs

Attention as a learned way to decide what context matters for each token.

How pretrained language models are adapted to a task or domain with supervised data.

A practical map of LLM evaluation risks: hallucination, prompt sensitivity, bias, contamination, and brittle benchmarks.

Why NLP evaluation needs metrics, uncertainty, human judgment, and task-specific error analysis.

Why LoRA and adapters are useful when full fine-tuning is too expensive or unstable.

Prompting as task specification, interface design, and evaluation risk.