REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted texts. While humans naturally anchor their understanding around key entities and concepts, neural models process text within rigid token windows, treating all interactions as equally important and missing critical semantic signals. We introduce REGENT, a neural re-ranking model that mimics human-like understanding by using entities as a "semantic skeleton" to guide attention. REGENT integrates relevance guidance directly into the attention mechanism, combining fine-grained lexical matching with high-level semantic reasoning. This relevance-guided attention enables the model to focus on conceptually important content while maintaining sensitivity to precise term matches. REGENT achieves new state-of-the-art performance in three challenging datasets, providing up to 108% improvement over BM25 and consistently outperforming strong baselines including ColBERT and RankVicuna. To our knowledge, this is the first work to successfully integrate entity semantics directly into neural attention, establishing a new paradigm for entity-aware information retrieval.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalSimilar Papers 제목 키워드 기반
The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems
We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible r…
Answer GenerationQuestion AnsweringRAGRetrieval-augmented GenerationREGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist …
In-Context LearningRetrievalType-enhanced Ensemble Triple Representation via Triple-aware Attention for Cross-lingual Entity Alignment
Entity alignment(EA) is a crucial task for integrating cross-lingual and cross-domain knowledge graphs(KGs), which aims to discover entities referring to the same real-world object from different KGs. Most existing metho…
DiversityEntity AlignmentKnowledge GraphsSpecificitySELFI: Selective Fusion of Identity for Generalizable Deepfake Detection
Face identity provides a powerful signal for deepfake detection. Prior studies show that even when not explicitly modeled, classifiers often learn identity features implicitly. This has led to conflicting views: some sup…
DeepFake DetectionFace RecognitionFace SwappingReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable
Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data c…
Autonomous Driving