用检索反馈训练大模型生成更利于找表的描述，提升检索效果。
Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
- 基于检索反馈构建偏好数据，用DPO优化描述生成
- 在TableQA等数据集上超越现有最佳方案，显著提升检索准确率
- 适合需要改进表格检索的NLP系统开发者
许多以表格为中心的自然语言处理任务（如NL2SQL）首先通过关键词搜索从大规模集合中检索相关表格。近期工作使用大模型生成自然语言表格描述以改善检索效果，但这些模型通常只优化流畅性而非检索有效性。我们提出Polaris，一种直接从检索反馈中训练大模型生成表格描述的系统。核心思想是：现有表格检索基准已包含该任务所需的监督信号——给定查询-表格相关性判断，为每张表生成多个候选描述，根据其BM25检索表现进行排序，形成偏好对，用于通过直接偏好优化（DPO）微调大模型。Polaris在生成前扩展缩写表名和列名，减少词汇不匹配。大量实验表明，Polaris显著优于当前最佳方案AutoDDG。更广泛地，我们的结果表明，检索基准可被重用于训练生成面向检索的元数据的大模型。
原文摘要 · Abstract (English)
Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generate natural-language table descriptions to improve retrieval, but they are typically optimized for fluency rather than retrieval effectiveness. We present Polaris, a system that trains an LLM to generate table descriptions directly from retrieval feedback. Our key insight is that existing table retrieval benchmarks already contain the supervision needed for this task: given query-table relevance judgments, we generate multiple candidate descriptions for each table, rank them by their BM25 retrieval effectiveness, and use the resulting preference pairs to fine-tune the LLM with Direct Preference Optimization (DPO). Polaris further expands abbreviated table and column names before generation to reduce vocabulary mismatch. Extensive experiments show that Polaris outperforms the state-of-the-art AutoDDG solution, often by a significant margin. More broadly, our results demonstrate that retrieval benchmarks can be repurposed as supervision for training LLMs to generate retrieval-oriented metadata.
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。