Lune

NeurIPS2024Top-tier venue

Generative Retrieval Meets Multi-Graded Relevance

Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng

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 (GR2^2). GR2^2 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 achieved by jointly optimizing the relevance and distinctness of docids through a combination of docid generation and autoencoder models. Second, we incorporate information about the relationship between relevance grades to guide the training process. We use a constrained contrastive training strategy to bring the representations of queries and the identifiers of their relevant documents closer together, based on their respective relevance grades. Extensive experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR2^2.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
  • Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval cites Training language models to follow instructions with human feedback
  • Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval cites A Simple Framework for Contrastive Learning of Visual Representations
  • Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval cites ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
  • Multi-level Relevance Document Identifier Learning for Generative Retrieval cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
  • A Parametric Memory Head for Continual Generative Retrieval cites Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Multi-level Relevance Document Identifier Learning for Generative RetrievalFuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang et al.ACL 2025 · 5 citations
  2. Lightweight and Direct Document Relevance Optimization for Generative Information RetrievalKidist Amde Mekonnen, Yubao Tang, Maarten de RijkeSIGIR 2025 · 3 citations
  3. Constrained Auto-Regressive Decoding Constrains Generative RetrievalShiguang Wu, Zhaochun Ren, Xin Xin, Jiyuan Yang et al.SIGIR 2025 · 3 citations
  4. Boosting Retrieval-Augmented Generation with Generation-Augmented Retrieval: A Co-Training ApproachYubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke et al.SIGIR 2025 · 2 citations
  5. A Parametric Memory Head for Continual Generative RetrievalKidist Amde Mekonnen, Yubao Tang, Maarten de RijkeSIGIR 2026

Builds on34

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  3. Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
  4. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
  5. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaSIGIR 2020 · 1,246 citations

Related papers

  1. Descriptive and Discriminative Document Identifiers for Generative RetrievalJiehan Cheng, Zhicheng Dou, Yutao Zhu, Xiaoxi LiAAAI 2025 · 4 citations
  2. DOGR: Leveraging Document-Oriented Contrastive Learning in Generative RetrievalPenghao Lu, Xin Dong, Yuansheng Zhou, Lei Cheng et al.AAAI 2025
  3. Enhancing Generative Retrieval with Reinforcement Learning from Relevance FeedbackYujia Zhou, Zhicheng Dou, Ji-Rong WenEMNLP 2023 · 14 citations
  4. Auto Search Indexer for End-to-End Document RetrievalTianchi Yang, Minghui Song, Zihan Zhang, Haizhen Huang et al.EMNLP Findings 2023 · 9 citations
  5. Generative Retrieval via Term Set GenerationPeitian Zhang, Zheng Liu, Yujia Zhou, Zhicheng Dou et al.SIGIR 2024 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines