Tag
DPR-BAG is a training-free, zero-shot framework that generates coherent biomedical abstracts from full-text articles by decomposing them into rhetorical facets, summarizing each with an LLM, and refining for coherence, achieving better novelty than baselines while maintaining factual consistency.
LaMSUM is a novel multi-level framework using LLMs to generate extractive summaries of large collections of harassment incident reports from citizen reporting platforms. The approach outperforms state-of-the-art extractive summarization methods and addresses challenges like limited LLM context windows and code-mixed language processing.