AI 中文总结
针对检索增强语言模型无法遵守负约束的问题，提出无需训练的重排序方法E-SENS，在ExcluIR数据集的四种嵌入模型上，于保留召回的同时减少了陷阱检索。
AI 中文摘要
检索增强语言模型在检索器提供用户明确排除概念的证据时，可能无法遵守负约束。除了明确否定外，查询可能要求包含一个概念同时排除另一个概念，或要求属于某一类别但与密切相关实例不同的实体。由于被排除的概念仍出现在查询文本中，密集检索器可能会为关于该概念的文档分配高相似度，即便用户要求避开它。我们提出E-SENS，一种无需训练的负敏感检索重排序方法。E-SENS为被排除侧提取一个紧凑的陷阱查询，并从原始查询的检索得分中减去陷阱查询相似度。在ExcluIR数据集上，E-SENS在四种嵌入模型中表现出明显的召回-违规权衡，并在保留召回的设置下减少了陷阱检索。
英文摘要
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.
