Reasoning-Aware Query-Focused Summarization over Multi-Table Data
This addresses the problem of extracting precise information from structured data for users needing summaries from multi-table queries, representing a strong specific gain rather than a foundational advancement.
The paper tackled query-focused summarization over multi-table data by proposing QueryTableSummarizer++, an end-to-end generative framework using LLMs, which significantly outperformed state-of-the-art baselines on benchmark metrics like BLEU, ROUGE, and F1-score.
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.