{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T06:14:29Z","timestamp":1771049669649,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3662344","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:07:42Z","timestamp":1770671262000},"page":"22318-22334","source":"Crossref","is-referenced-by-count":0,"title":["DKC-LLM: Dynamic Knowledge Caching for Large Language Models in Business Applications"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5942-5802","authenticated-orcid":false,"given":"Ayesha","family":"Khaliq","sequence":"first","affiliation":[{"name":"Iqra University, Karachi, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7126-7026","authenticated-orcid":false,"given":"Kolawole J.","family":"Adebayo","sequence":"additional","affiliation":[{"name":"Computer Science Department, Adapt Centre, Maynooth University, Maynooth, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/12460125.2024.2410040"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.09.178"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688990"},{"key":"ref5","article-title":"Improving the reliability of LLMs: Combining CoT, RAG, self-consistency, and self-verification","author":"Kumar","year":"2025","journal-title":"arXiv:2505.09031"},{"key":"ref6","volume-title":"RAG-Based Chat Application Using LLMs: A Case Study of Vikram Sarabhai Library IIM Ahmedabad","author":"Chand","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3768628"},{"key":"ref9","article-title":"Retrieval augmented generation: An evaluation of RAG-based chatbot for customer support","author":"Analytics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ccis63231.2024.10932014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2025.103995"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icacrs62842.2024.10841586"},{"key":"ref13","article-title":"CAPRAG: A large language model solution for customer service and automatic reporting using vector and graph retrieval-augmented generation","volume-title":"arXiv:2501.13993","author":"Landolsi","year":"2025"},{"key":"ref14","article-title":"Retail-GPT: Leveraging retrieval augmented generation (RAG) for building e-commerce chat assistants","author":"Amaral Teixeira de Freitas","year":"2024","journal-title":"arXiv:2408.08925"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"ref16","article-title":"Dynamic retrieval-augmented generation","author":"Shapkin","year":"2023","journal-title":"arXiv:2312.08976"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.54364\/AAIML.2023.1191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref19","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.981"},{"key":"ref22","article-title":"Gemma: Open models based on Gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv:2403.08295"},{"key":"ref23","article-title":"Passage re-ranking with BERT","author":"Nogueira","year":"2019","journal-title":"arXiv:1901.04085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-024-00898-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1145\/3690624.3709194","article-title":"PipeRAG: Fast retrieval-augmented generation via adaptive pipeline parallelism","author":"Jiang","year":"2025"},{"key":"ref27","article-title":"Inference scaling for long-context retrieval augmented generation","author":"Yue","year":"2024","journal-title":"arXiv:2410.04343"},{"key":"ref28","article-title":"CacheFocus: Dynamic cache re-positioning for efficient retrieval-augmented generation","author":"Lee","year":"2025","journal-title":"arXiv:2502.11101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696086"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3725273"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696098"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3721146.3721941"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2991\/978-94-6463-540-9_69"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc9030067"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/indicon63790.2024.10958508"},{"key":"ref36","article-title":"Etalon: Holistic performance evaluation framework for LLM inference systems","author":"Agrawal","year":"2024","journal-title":"arXiv:2407.07000"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dettmers"},{"key":"ref40","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024","journal-title":"arXiv:2402.13116"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref42","article-title":"Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference","author":"Warner","year":"2024","journal-title":"arXiv:2412.13663"},{"key":"ref43","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref44","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref45","article-title":"Phi-4 technical report","volume-title":"arXiv:2412.08905","author":"Abdin","year":"2024"},{"key":"ref46","article-title":"Efficient prompt caching via embedding similarity","author":"Zhu","year":"2024","journal-title":"arXiv:2402.01173"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"issue":"1","key":"ref48","first-page":"7","article-title":"Preprocessing techniques for text mining","volume":"5","author":"Kannan","year":"2014","journal-title":"Int. J. Comput. Sci. Commun. Netw."},{"key":"ref49","article-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024","journal-title":"arXiv:2401.01313"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731116"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685905"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/nlp.2024.53"},{"key":"ref53","article-title":"Retrieval-augmented generation for natural language processing: A survey","author":"Wu","year":"2024","journal-title":"arXiv:2407.13193"},{"key":"ref54","article-title":"Retrieval-augmented generation: A comprehensive survey of architectures, enhancements, and robustness frontiers","author":"Sharma","year":"2025","journal-title":"arXiv:2506.00054"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/mvt.2025.3608414"},{"key":"ref56","first-page":"113134","article-title":"ArkVale: Efficient generative LLM inference with recallable key-value eviction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref57","article-title":"Compute or load KV cache? Why not both?","author":"Jin","year":"2024","journal-title":"arXiv:2410.03065"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.623"},{"key":"ref59","article-title":"Semantic caching of contextual summaries for efficient question-answering with language models","author":"Couturier","year":"2025","journal-title":"arXiv:2505.11271"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/math13050856"},{"key":"ref61","first-page":"29","article-title":"Hallucination detection in LLM-enriched product listings","volume-title":"Proc. Workshop E-Commerce NLP@LREC-COLING","author":"Jiang"},{"key":"ref62","volume-title":"NLP@LREC-COLING","year":"2024"},{"key":"ref63","article-title":"Blueprinting AI economics: Cost assessment framework for business stakeholders to navigate key aspects in prompt engineering, prompt automation, and fine-tuning LLMs","author":"Sulaiman","year":"2024"},{"key":"ref64","article-title":"FrugalGPT: How to use large language models while reducing cost and improving performance","author":"Chen","year":"2023","journal-title":"arXiv:2305.05176"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.5119925"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2023.100140"},{"key":"ref67","volume-title":"Enterprise AI in the Cloud: A Practical Guide to Deploying End-to-End Machine Learning and ChatGPT Solutions","author":"Jay","year":"2023"},{"key":"ref68","article-title":"Hallucinations or attention misdirection? The path to strategic value extraction in business using large language models","author":"Ioste","year":"2024","journal-title":"arXiv:2402.14002"},{"key":"ref69","first-page":"1","article-title":"Improving customer journeys: Data-driven LLM chatbot customization","author":"Melo","year":"2024","journal-title":"Available at SSRN"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/iwqos61813.2024.10682957"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0269"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1062"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11380191.pdf?arnumber=11380191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:47:15Z","timestamp":1771048035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11380191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3662344","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}