用大模型生成更高质量的检索训练数据，提升信息检索效果。
InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems
- 用对比偏好优化微调查询生成模型，提高生成质量。
- 动态提示链优化使生成结果更准确，减少过滤依赖。
- 适合做检索系统数据增强的研究者和工程师使用。
本文重新审视并扩展了神经信息检索（NIR）中合成查询生成流程，利用InPars Toolkit这一可复现的端到端框架，基于大语言模型（LLMs）生成训练数据。在SciFact基准上评估了原始InPars、InPars-V2和Promptagator流程的可复现性，并使用开源重排序器和生成模型验证其有效性。在此基础上，提出两项关键改进：(1) 通过对比偏好优化（CPO）微调查询生成LLM，提升生成查询的信号质量；(2) 采用DSPy框架将静态提示模板替换为动态的思维链（CoT）优化提示。实验表明，两项改进均降低了对激进过滤的依赖，同时提升了检索性能。所有代码、模型及合成数据集均已公开，支持后续研究：https://github.com/danilotpnta/IR2-project。
原文摘要 · Abstract (English)
This work revisits and extends synthetic query generation pipelines for Neural Information Retrieval (NIR) by leveraging the InPars Toolkit, a reproducible, end-to-end framework for generating training data using large language models (LLMs). We first assess the reproducibility of the original InPars, InPars-V2, and Promptagator pipelines on the SciFact benchmark and validate their effectiveness using open-source reranker and generator models. Building on this foundation, we introduce two key extensions to the pipeline: (1) fine-tuning a query generator LLM via Contrastive Preference Optimization (CPO) to improve the signal quality in generated queries, and (2) replacing static prompt templates with dynamic, Chain-of-Thought (CoT) optimized prompts using the DSPy framework. Our results show that both extensions reduce the need for aggressive filtering while improving retrieval performance. All code, models, and synthetic datasets are publicly released to support further research at: \href{https://github.com/danilotpnta/IR2-project}{this https URL}.
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。