Generative Retrieval Meets Multi-graded Relevance

Abstract

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches are limited to scenarios with binary relevance data, overlooking the potential for documents to have multi-graded relevance. Extending generative retrieval to accommodate multi-graded relevance poses challenges, including the need to reconcile likelihood probabilities for docid pairs and the possibility of multiple relevant documents sharing the same identifier. To address these challenges, we introduce a framework called GRaded Generative Retrieval (GR\(^2\)). GR\(^2\) focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. First, we create identifiers that are both semantically relevant and sufficiently distinct to represent individual documents effectively. This is

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keytang2024generative

Related papers

• Generative Retrieval As Multi-vector Dense Retrieval (2024)8.60
• Does Generative Retrieval Overcome The Limitations Of Dense Retrieval? (2025)0.00
• Lightweight And Direct Document Relevance Optimization For Generative Information Retrieval (2025)4.52
• Listwise Generative Retrieval Models Via A Sequential Learning Process (2024)8.60
• Generative Dense Retrieval: Memory Can Be A Burden (2024)4.52
• Continual Learning For Generative Retrieval Over Dynamic Corpora (2023)11.49
• Generative Retrieval As Dense Retrieval (2023)0.00
• Multi-step Semantic Reasoning In Generative Retrieval (2026)0.00