{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/scalable-and-effective-generative-information","title":"Scalable and Effective Generative Information Retrieval","arxiv_id":"2311.09134","date":"2023-11-15","proceeding":null,"authors":["Hansi Zeng","Chen Luo","Bowen Jin","Sheikh Muhammad Sarwar","Tianxin Wei","Hamed Zamani"],"abstract":"Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequences of document ID tokens. These generative retrieval models cast the retrieval problem to a document ID generation problem for each given query. Despite their elegant design, existing generative retrieval models only perform well on artificially-constructed and small-scale collections. This has led to serious skepticism in the research community on their real-world impact. This paper represents an important milestone in generative retrieval research by showing, for the first time, that generative retrieval models can be trained to perform effectively on large-scale standard retrieval benchmarks. For doing so, we propose RIPOR- an optimization framework for generative retrieval that can be adopted by any encoder-decoder architecture. RIPOR is designed based on two often-overlooked fundamental design considerations in generative retrieval. First, given the sequential decoding nature of document ID generation, assigning accurate relevance scores to documents based on the whole document ID sequence is not sufficient. To address this issue, RIPOR introduces a novel prefix-oriented ranking optimization algorithm. Second, initial document IDs should be constructed based on relevance associations between queries and documents, instead of the syntactic and semantic information in the documents. RIPOR addresses this issue using a relevance-based document ID construction approach that quantizes relevance-based representations learned for documents. Evaluation on MSMARCO and TREC Deep Learning Track reveals that RIPOR surpasses state-of-the-art generative retrieval models by a large margin (e.g., 30.5% MRR improvements on MS MARCO Dev Set), and perform better on par with popular dense retrieval models.","url_abs":"https://arxiv.org/abs/2311.09134v1","url_pdf":"https://arxiv.org/pdf/2311.09134v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scalable-and-effective-generative-information","repo_url":"https://github.com/hansizeng/ripor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"scalable-and-effective-generative-information","repo_url":"https://github.com/HongruCai/SLGR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"scalable-and-effective-generative-information","repo_url":"https://github.com/hansizeng/pag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09134"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hansizeng/ripor","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hansizeng/pag","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HongruCai/SLGR","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"029a2a2450f47a82","entry":"init_regularizer","repo":"hansizeng/ripor","repo_kind":"official","path":"t5_pretrainer/losses/regulariaztion.py","file_url":"https://github.com/hansizeng/ripor/blob/HEAD/t5_pretrainer/losses/regulariaztion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"029a2a2450f47a82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}