LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction
This work addresses the problem of low objectivity in news summarization for users needing concise event reports, though it appears incremental as it builds on existing extract-rewrite methods with specific modifications.
The paper tackles the challenge of subjective bias in multi-document news summarization by focusing on extracting and coherently presenting the main event from related documents, achieving improved performance over baselines in content coverage, coherence, and informativeness.
Multi-document summarization is a challenging task due to its inherent subjective bias, highlighted by the low inter-annotator ROUGE-1 score of 0.4 among DUC-2004 reference summaries. In this work, we aim to enhance the objectivity of news summarization by focusing on the main event of a group of related news documents and presenting it coherently with sufficient context. Our primary objective is to succinctly report the main event, ensuring that the summary remains objective and informative. To achieve this, we employ an extract-rewrite approach that incorporates a main-event biased monotone-submodular function for content selection. This enables us to extract the most crucial information related to the main event from the document cluster. To ensure coherence, we utilize a fine-tuned Language Model (LLM) for rewriting the extracted content into a coherent text. The evaluation using objective metrics and human evaluators confirms the effectiveness of our approach, as it surpasses potential baselines, demonstrating excellence in both content coverage, coherence, and informativeness.