{"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/rella-retrieval-enhanced-large-language","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","arxiv_id":"2308.11131","date":"2023-08-22","proceeding":null,"authors":["Jianghao Lin","Rong Shan","Chenxu Zhu","Kounianhua Du","Bo Chen","Shigang Quan","Ruiming Tang","Yong Yu","Weinan Zhang"],"abstract":"With large language models (LLMs) achieving remarkable breakthroughs in natural language processing (NLP) domains, LLM-enhanced recommender systems have received much attention and have been actively explored currently. In this paper, we focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks. First and foremost, we identify and formulate the lifelong sequential behavior incomprehension problem for LLMs in recommendation domains, i.e., LLMs fail to extract useful information from a textual context of long user behavior sequence, even if the length of context is far from reaching the context limitation of LLMs. To address such an issue and improve the recommendation performance of LLMs, we propose a novel framework, namely Retrieval-enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings. For zero-shot recommendation, we perform semantic user behavior retrieval (SUBR) to improve the data quality of testing samples, which greatly reduces the difficulty for LLMs to extract the essential knowledge from user behavior sequences. As for few-shot recommendation, we further design retrieval-enhanced instruction tuning (ReiT) by adopting SUBR as a data augmentation technique for training samples. Specifically, we develop a mixed training dataset consisting of both the original data samples and their retrieval-enhanced counterparts. We conduct extensive experiments on three real-world public datasets to demonstrate the superiority of ReLLa compared with existing baseline models, as well as its capability for lifelong sequential behavior comprehension. To be highlighted, with only less than 10% training samples, few-shot ReLLa can outperform traditional CTR models that are trained on the entire training set (e.g., DCNv2, DIN, SIM). The code is available \\url{https://github.com/LaVieEnRose365/ReLLa}.","url_abs":"https://arxiv.org/abs/2308.11131v6","url_pdf":"https://arxiv.org/pdf/2308.11131v6.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":"rella-retrieval-enhanced-large-language","repo_url":"https://github.com/lavieenrose365/rella","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.11131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11131"}},"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/lavieenrose365/rella","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"2e09afada03cc9f1","entry":"compute_metrics","repo":"lavieenrose365/rella","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e09afada03cc9f1"}},{"code_sha256_prefix":"215b58cabb52b84b","entry":"get_template","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_BookCrossing.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_BookCrossing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"215b58cabb52b84b"}},{"code_sha256_prefix":"9b2107ea7ebc55bb","entry":"get_template","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_ml1m.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_ml1m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b2107ea7ebc55bb"}},{"code_sha256_prefix":"7295846e5ff4d44d","entry":"get_template","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_ml25m.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_ml25m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7295846e5ff4d44d"}},{"code_sha256_prefix":"82d07bd787abe764","entry":"preprocess_logits_for_metrics","repo":"lavieenrose365/rella","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82d07bd787abe764"}},{"code_sha256_prefix":"28989ed2d784c752","entry":"preprocess_logits_for_metrics","repo":"lavieenrose365/rella","repo_kind":"official","path":"inference.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28989ed2d784c752"}},{"code_sha256_prefix":"6dbd845a63cc9847","entry":"row_to_prompt","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_BookCrossing.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_BookCrossing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6dbd845a63cc9847"}},{"code_sha256_prefix":"837190389192b1f1","entry":"row_to_prompt","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_ml25m.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_ml25m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"837190389192b1f1"}},{"code_sha256_prefix":"09c34129a8d23513","entry":"row_to_prompt","repo":"lavieenrose365/rella","repo_kind":"official","path":"load_prompt_ml1m.py","file_url":"https://github.com/lavieenrose365/rella/blob/HEAD/load_prompt_ml1m.py","link_basis":"first_harvest_node","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":"09c34129a8d23513"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}