This work introduces E-SENS, a training-free reranking method for negation-sensitive retrieval that shows a clear recall-violation trade-off across four embedding models and reduces trap retrieval at recall-preserving settings.
Abstract
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.
Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effectiveness varies primarily with candidate-pool redundancy, in a pattern consistent with the number of distinct evidence p...
Guillaume Brouillette, Faustin Kagabo, Usef Faghihi et al.· 0 citations
This work proposes PAO (Positive-Advantage-Only), a selective RL optimization method that selectively applies gradient updates only to retrieved items with positive advantages, effectively pulling query embed- dings toward high-reward regions while preserving global topo- logical stability.
Shao-Wei Wei, Chong Huang, Songtao Fang et al.· 0 citations
Retrieval-Augmented Generation (RAG) systems typically apply identical retrieval logic to all user queries, overlooking that different query intents depend on fundamentally different document relationships. We propose QMEG, a query-aware retrieval framework that constructs a multi-relational evidence graph with five ac...
Jia-Run Pan, Yu-Ling Fan, Li Ma et al.· 2026 3rd International Confe...· 0 citations
Bag-of-Documents Specificity (BoDS) is introduced, a two-stage approach that operationalizes query specificity as intent coherence : how tightly a query’s engaged documents cluster in embedding space using the mean resultant length of a query’s associated document vectors.
Aritra Mandal, Daniel Tunkelang, Zhe Wu· 0 citations
This paper introduces AutoConcept, a training-free reranker that converts concept evidence into an interpretable memory that positions AutoConcept as an interpretable concept-memory reranker for product-style CIR galleries with available metadata.
Multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention, demonstrates that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based histori...
Tien N. Nguyen, Emanuela Boros, Ahmed Hamdi et al.· 0 citations
