RPDR：基于回程预测的数据增强框架用于长尾问答
RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering
AI总结：
RPDR通过数据增强框架提升长尾问答性能，利用回程预测选择易学实例并动态路由查询以优化检索效果。
摘要：
长尾问答给大语言模型（LLMs）带来了巨大挑战，因为它们在获取和准确回忆较少见知识方面的能力有限。检索增强生成（RAG）系统通过整合外部检索机制显示出缓解这一限制的潜力。然而，密集检索模型在泛化到罕见或小众知识时仍面临相同困难。在本研究中，我们引入了RPDR，一种新颖的数据增强框架，选择高质量易学的训练数据，以增强密集检索器。我们的方法围绕三个核心组件：合成数据生成、利用回程预测进行数据选择以识别易学实例，以及使用这些实例进行检索器训练。我们在两个长尾检索基准测试集PopQA和EntityQuestion上评估了RPDR，证明其在现有检索器如BM25和Contriver上取得了显著改进，尤其是在极端长尾类别上。我们通过详细的人类分析识别了RPDR的优势和局限性，并提出了一种动态路由机制，动态地将查询路由到专门的检索模块，以进一步提高检索性能。
英文摘要：
Long-tail question answering presents significant challenges for large language models (LLMs) due to their limited ability to acquire and accurately recall less common knowledge. Retrieval-augmented generation (RAG) systems have shown great promise in mitigating this limitation by integrating external retrieval mechanisms. However, dense retrieval models often face the same difficulties when generalizing to rare or niche knowledge. In this study, we introduce RPDR, a novel data augmentation framework that selects high-quality easy-to-learn training data, to enhance dense retrievers. Our approach is built around three core components: synthetic data generation, data selection with Round-Trip prediction to identify easy-to-learn instances, and retriever training with these instances. We evaluate RPDR on two long-tail retrieval benchmarks, PopQA and EntityQuestion, demonstrating substantial improvements over existing retrievers like BM25 and Contriver, especially on extremely long-tail categories. We identify the strengths and limitations of RPDR through detailed human analysis and propose a dynamic routing mechanism to dynamically route queries to specialized retrieval modules to further improve retrieval performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
