用大模型直接生成多表查询摘要，省去繁琐预处理。
Reasoning-Aware Query-Focused Summarization over Multi-Table Data
- 用表感知预训练+查询对齐微调+强化学习，端到端生成摘要。
- 在基准数据集上超越现有方法，BLEU、ROUGE、F1均显著提升。
- 适合需要跨领域、复杂逻辑推理的结构化数据摘要场景。
面向多表数据的查询聚焦摘要是一项挑战性且关键的任务，旨在从结构化数据中提取精确相关的信息。现有方法通常依赖复杂的预处理步骤，难以跨领域泛化，且难以处理多表查询所需的逻辑推理。本文提出 QueryTableSummarizer++，一种基于大语言模型（LLMs）的端到端生成框架，通过表感知预训练、查询对齐微调以及带反馈的强化学习进行增强。该方法无需中间序列化步骤，可直接生成与查询相关的摘要。在基准数据集上的实验表明，QueryTableSummarizer++ 在 BLEU、ROUGE 和 F1 分数上显著优于现有最优基线。额外分析显示其具备良好的可扩展性、跨领域泛化能力及对复杂查询的鲁棒处理能力。人工评估进一步验证了生成摘要的高质量与实际可用性，确立了 QueryTableSummarizer++ 在多表摘要任务中的高效性。
原文摘要 · Abstract (English)
Query-focused summarization over multi-table data is a challenging yet critical task for extracting precise and relevant information from structured data. Existing methods often rely on complex preprocessing steps and struggle to generalize across domains or handle the logical reasoning required for multi-table queries. In this paper, we propose QueryTableSummarizer++, an end-to-end generative framework leveraging large language models (LLMs) enhanced with table-aware pre-training, query-aligned fine-tuning, and reinforcement learning with feedback. Our method eliminates the need for intermediate serialization steps and directly generates query-relevant summaries. Experiments on a benchmark dataset demonstrate that QueryTableSummarizer++ significantly outperforms state-of-the-art baselines in terms of BLEU, ROUGE, and F1-score. Additional analyses highlight its scalability, generalization across domains, and robust handling of complex queries. Human evaluation further validates the superior quality and practical applicability of the generated summaries, establishing QueryTableSummarizer++ as a highly effective solution for multi-table summarization tasks.
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。