Polaris：基于检索反馈学习生成表格描述
Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
浏览论文内容
中文总结 AI 辅助
Polaris是基于检索反馈训练LLM生成表格描述的系统，通过BM25排序和DPO微调优化检索效果，性能优于AutoDDG，证明检索基准可用于训练LLM生成面向检索的元数据。
中文摘要 AI 辅助
许多以表格为中心的自然语言处理任务，如NL2SQL，首先会通过关键词搜索从大型集合中检索相关表格。近期研究使用大型语言模型（LLM）生成自然语言表格描述以改进检索效果，但这些模型通常针对流畅度而非检索效果进行优化。我们提出Polaris系统，该系统训练LLM直接从检索反馈中生成表格描述。我们的核心见解是，现有表格检索基准已包含此任务所需的监督信息：给定查询-表格相关性判断，我们为每个表格生成多个候选描述，通过BM25检索效果对其排序，并使用得到的偏好对通过直接偏好优化（DPO）微调LLM。Polaris还在生成前扩展缩写的表格和列名，以减少词汇不匹配。大量实验表明，Polaris的性能优于最先进的AutoDDG解决方案，且通常优势显著。更广泛而言，我们的结果证明，检索基准可被重新用作训练LLM生成面向检索的元数据的监督信息。
英文摘要
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.
发表机构
- University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
机构由 AI 辅助整理，请以论文原文为准。
