mlsanityData to 7 Oct 2026

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

arXiv 2608.30130 ↗First posted 31 Aug 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 10 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

9 of 10 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval10 Mar

Other references · 8

  1. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  2. 2023Language models are not naysayers: An analysis of language models on negation benchmarkscited by 73
  3. 2025Vision-Language Models Do Not Understand Negationcited by 69
  4. 2022What Are You Token About? Dense Retrieval as Distributions Over the Vocabularycited by 28
  5. 2023NevIR: Negation in Neural Information Retrievalcited by 28
  6. 2024BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?cited by 6
  7. 2025Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queriescited by 3
  8. 2026Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QAcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Embedding-Based Context-Aware Reranker
  2. 2026ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning
  3. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  4. 2025SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Context
  6. 2025DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers
  7. 2024Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining
  8. 2026AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation