{"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/recitation-augmented-language-models","title":"Recitation-Augmented Language Models","arxiv_id":"2210.01296","date":"2022-10-04","proceeding":null,"authors":["Zhiqing Sun","Xuezhi Wang","Yi Tay","Yiming Yang","Denny Zhou"],"abstract":"We propose a new paradigm to help Large Language Models (LLMs) generate more accurate factual knowledge without retrieving from an external corpus, called RECITation-augmented gEneration (RECITE). Different from retrieval-augmented language models that retrieve relevant documents before generating the outputs, given an input, RECITE first recites one or several relevant passages from LLMs' own memory via sampling, and then produces the final answers. We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks. Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance in various closed-book question answering (CBQA) tasks. In experiments, we verify the effectiveness of \\method~on four pre-trained models (PaLM, UL2, OPT, and Codex) and three CBQA tasks (Natural Questions, TriviaQA, and HotpotQA). Our code is available at \"https://github.com/Edward-Sun/RECITE\".","url_abs":"https://arxiv.org/abs/2210.01296v2","url_pdf":"https://arxiv.org/pdf/2210.01296v2.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":"recitation-augmented-language-models","repo_url":"https://github.com/edward-sun/recite","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[{"method_slug":"opt","method_name":"OPT"},{"method_slug":"ul2","method_name":"UL2"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.01296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01296"}},"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/edward-sun/recite","reach":null}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"5eb45a0beb746691","entry":"nq_target_processing_fn","repo":"Edward-Sun/RECITE","repo_kind":"official","path":"recite/codex_experiments/run_natural_questions.py","file_url":"https://github.com/Edward-Sun/RECITE/blob/HEAD/recite/codex_experiments/run_natural_questions.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5eb45a0beb746691"}},{"code_sha256_prefix":"02d0803d206c8868","entry":"openai_complete","repo":"edward-sun/recite","repo_kind":"official","path":"recite/codex_experiments/utils.py","file_url":"https://github.com/edward-sun/recite/blob/HEAD/recite/codex_experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"02d0803d206c8868"}},{"code_sha256_prefix":"525863047ce7b158","entry":"recite_predict_call","repo":"edward-sun/recite","repo_kind":"official","path":"recite/codex_experiments/utils.py","file_url":"https://github.com/edward-sun/recite/blob/HEAD/recite/codex_experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"525863047ce7b158"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}