利用主事件偏向的单调子模内容提取的基于大语言模型的多文档摘要
LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction
AI总结：
针对多文档摘要主观偏差大的问题，提出融入主事件偏向单调子模函数的提取-改写方法，结合微调LLM生成连贯摘要，在内容覆盖等方面超越基线。
摘要：
多文档摘要是一项具有挑战性的任务，因其存在固有主观偏差，这一点在DUC-2004参考摘要之间标注者间ROUGE-1分数仅为0.4的低水平中尤为凸显。本研究中，我们聚焦一组相关新闻文档的主事件，并以充足上下文连贯呈现，旨在提升新闻摘要的客观性。我们的核心目标是简洁报道主事件，确保摘要兼具客观性与信息性。为此，我们采用“提取-改写”方法，该方法融入主事件偏向的单调子模函数用于内容选择，使我们能从文档簇中提取与主事件相关的最关键信息。为保证连贯性，我们使用微调后的大语言模型（LLM）将提取的内容改写为连贯文本。通过客观指标与人工评估者开展的评估证实了我们方法的有效性，其性能超越了潜在基线，在内容覆盖度、连贯性和信息性方面均表现优异。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
