对比压缩与全文方法在长文档摘要中的表现，发现后者更优但需结合两者优势。
Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches
- 比较压缩与全文两种长文本摘要方法的性能差异。
- 全文本方法在多数场景下表现最佳，压缩法在中间阶段有潜力。
- 建议融合两类方法以提升大规模多文档摘要效果。
自动总结大型文本集合对新闻、学术研究、法律工作等领域具有重要价值。本文对比了两类大规模多文档摘要（MDS）系统：压缩型与全文型。压缩方法采用多阶段流程，常导致信息损失；全文方法借助长上下文推理技术，可实现无损摘要。我们在三个数据集上评估，每个摘要对应约一百篇文档，涵盖 Llama-3.1、Command-R、Jamba-1.5-Mini 等长上下文大模型及检索增强、层次化、增量式等压缩方法。结果表明，全文方法与检索型方法在多数设置中表现最优。进一步分析显示，压缩方法在中间阶段保留关键信息能力较强，甚至优于全上下文方法，但因多阶段流程和缺乏全局上下文而产生信息丢失。研究强调需发展融合压缩与全文的混合方法，以实现最优的大规模多文档摘要性能。
原文摘要 · Abstract (English)
Automatically summarizing large text collections is a valuable tool for document research, with applications in journalism, academic research, legal work, and many other fields. In this work, we contrast two classes of systems for large-scale multi-document summarization (MDS): compression and full-text. Compression-based methods use a multi-stage pipeline and often lead to lossy summaries. Full-text methods promise a lossless summary by relying on recent advances in long-context reasoning. To understand their utility on large-scale MDS, we evaluated them on three datasets, each containing approximately one hundred documents per summary. Our experiments cover a diverse set of long-context transformers (Llama-3.1, Command-R, Jamba-1.5-Mini) and compression methods (retrieval-augmented, hierarchical, incremental). Overall, we find that full-text and retrieval methods perform the best in most settings. With further analysis into the salient information retention patterns, we show that compression-based methods show strong promise at intermediate stages, even outperforming full-context. However, they suffer information loss due to their multi-stage pipeline and lack of global context. Our results highlight the need to develop hybrid approaches that combine compression and full-text approaches for optimal performance on large-scale multi-document summarization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。