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

arXiv: https://arxiv.org/abs/2608.30130 · HTML: https://mlsanity.com/paper/2608.30130/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 9 of 9)

- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Language models are not naysayers: An analysis of language models on negation benchmarks](https://mlsanity.com/paper/2306.08189/) (2023)
- [Vision-Language Models Do Not Understand Negation](https://mlsanity.com/paper/2501.09425/) (2025)
- [NevIR: Negation in Neural Information Retrieval](https://mlsanity.com/paper/2305.07614/) (2023)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?](https://mlsanity.com/paper/2411.12235/) (2024)
- [Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries](https://mlsanity.com/paper/2505.22299/) (2025)
- [DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval](https://mlsanity.com/paper/2603.09185/) (2026)
- [Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA](https://mlsanity.com/paper/2603.17580/) (2026)

## 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.