Lune

SIGIR2025Top-tier venue

Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval

Kidist Amde Mekonnen, Yubao Tang, Maarten de Rijke

Abstract

Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task, allowing for end-to-end optimization toward a unified global retrieval objective. However, existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. While reinforcement learning-based methods, such as reinforcement learning from relevance feedback (RLRF), aim to address this misalignment through reward modeling, they introduce significant complexity, requiring the optimization of an auxiliary reward function followed by reinforcement fine-tuning, which is computationally expensive and often unstable. To address these challenges, we propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking, eliminating the need for explicit reward modeling and reinforcement learning. Experimental results on benchmark datasets, including MS MARCO document and Natural Questions, show that DDRO outperforms reinforcement learning-based methods, achieving a 7.4% improvement in MRR@10 for MS MARCO and a 19.9% improvement for Natural Questions. These findings highlight DDRO's potential to enhance retrieval effectiveness with a simplified optimization approach. By framing alignment as a direct optimization problem, DDRO simplifies the ranking optimization pipeline of GenIR models while offering a viable alternative to reinforcement learning-based methods.

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.

2 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

  • Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Training language models to follow instructions with human feedback
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Distilling Large Embeddings via Hyperspherical Householder QuantizationYihang Wang, Bin Wu, Yueyang Su, Tianfu Zhang et al.ACL 2026
  2. A Parametric Memory Head for Continual Generative RetrievalKidist Amde Mekonnen, Yubao Tang, Maarten de RijkeSIGIR 2026

Builds on31

  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. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
  3. 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
  4. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  5. Deduplicating Training Data Makes Language Models BetterKatherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang et al.ACL 2022 · 844 citations

Related papers

  1. Enhancing Generative Retrieval with Reinforcement Learning from Relevance FeedbackYujia Zhou, Zhicheng Dou, Ji-Rong WenEMNLP 2023 · 14 citations
  2. Learning to Tokenize for Generative RetrievalWeiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang et al.NeurIPS 2023 · 151 citations
  3. DiffusionRet: Diffusion-Enhanced Generative Retriever using Constrained DecodingShanbao Qiao, Xuebing Liu, Seung-Hoon NaEMNLP Findings 2023 · 2 citations
  4. DOGR: Leveraging Document-Oriented Contrastive Learning in Generative RetrievalPenghao Lu, Xin Dong, Yuansheng Zhou, Lei Cheng et al.AAAI 2025
  5. Multi-level Relevance Document Identifier Learning for Generative RetrievalFuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang et al.ACL 2025 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines