解决检索模型误选用户排除概念的问题，提升负约束感知能力。
E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval
- 通过构建排除概念的简短陷阱查询，从原始相似度中减去其影响。
- 在四个嵌入模型上均有效降低召回率损失下的错误检索率。
- 无需训练，适配各类检索系统，尤其适合需严格排除干扰项的场景。
检索增强语言模型在检索器提供用户明确排除的概念证据时，可能无法遵守负约束。查询可能要求包含某一概念但排除另一相关概念，或要求属于某类别但不同于特定实例。由于排除概念仍出现在查询文本中，密集检索器可能对其文档赋予高相似度。我们提出E-SENS，一种无需训练的负约束敏感重排序方法。E-SENS为被排除项提取一个紧凑的陷阱查询，并将其相似度从原查询检索得分中减去。在ExcluIR数据集上，E-SENS在四种嵌入模型中均展现出清晰的召回-违规权衡，在保持召回率的设置下显著减少陷阱检索。
原文摘要 · Abstract (English)
Retrieval-augmented language models can fail to respect negative constraints when the retriever supplies evidence about concepts the user explicitly excluded. Beyond explicit negation, queries may ask for answers that include one concept while excluding another, or for entities that belong to a category but differ from a closely related instance. Because the excluded concept still appears in the query text, dense retrievers may assign high similarity to documents about that concept even when the user asks to avoid it. We introduce E-SENS, a training-free reranking method for negation-sensitive retrieval. E-SENS extracts a compact trap query for the excluded side and subtracts trap-query similarity from the original-query retrieval score. On ExcluIR, E-SENS shows a clear recall-violation trade-off across four embedding models and reduces trap retrieval at recall-preserving settings.
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。