Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Natural language processing and large language models
NLP research today centres on large language models: how to evaluate their knowledge and reasoning, how they write code and act as agents, how retrieval grounds them, how to adapt them cheaply, how they work internally, and how safe they are. Evaluation uses public benchmarks scored by exact match, accuracy, pass rates or judged success, with model versions, prompts and decoding settings stated and uncertainty reported over items and runs.