OBLIQ-Bench：揭示现代检索器中被忽视的瓶颈——潜在与隐式查询
OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
AI总结：
针对现有检索基准饱和但实际搜索问题未解决的现象，提出一类“倾斜查询”并构建OBLIQ-Bench基准，揭示检索与验证之间的不对称性，即推理LLM能可靠识别潜在相关性但检索管道无法召回多数相关文档。
摘要：
检索基准日益饱和，但我们认为高效搜索远非已解决的问题。我们识别出一类称为“倾斜”的查询，它们寻求实例化潜在模式的文档，例如找到所有表达隐式立场的推文、展示特定失败模式的聊天记录或匹配抽象场景的转录文本。我们研究了倾斜性产生的三种机制，并引入了OBLIQ-Bench，这是一套基于真实长尾语料库的五个倾斜搜索问题。OBLIQ-Bench揭示了检索与验证之间一个被忽视的不对称性：当相关文档被呈现时，推理LLM能可靠地识别潜在相关性，但即使是复杂的检索管道也无法首先召回大多数相关文档。我们希望OBLIQ-Bench能推动研究高效捕获大规模语料库中潜在模式和隐式信号的检索架构。
英文摘要：
Retrieval benchmarks are increasingly saturating, but we argue that efficient search is far from a solved problem. We identify a class of queries we call oblique, which seek documents that instantiate a latent pattern, like finding all tweets that express an implicit stance, chat logs that demonstrate a particular failure mode, or transcripts that match an abstract scenario. We study three mechanisms through which obliqueness may arise and introduce OBLIQ-Bench, a suite of five oblique search problems over real long-tail corpora. OBLIQ-Bench exposes an overlooked asymmetry between retrieval and verification, where reasoning LLMs reliably recognize latent relevance whenever relevant documents are surfaced, but even sophisticated retrieval pipelines fail to surface most relevant documents in the first place. We hope that OBLIQ-Bench will drive research into retrieval architectures that efficiently capture latent patterns and implicit signals in large corpora.
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。
