SOURCE-LINKED INTELLIGENCE

E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global