{"ID":2844204,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.07838","arxiv_id":"2601.07838","title":"A survey: Information search time optimization based on RAG (Retrieval Augmentation Generation) chatbot","abstract":"Retrieval-Augmented Generation (RAG) based chatbots are not only useful for information retrieval through questionanswering but also for making complex decisions based on injected private data.we present a survey on how much search time can be saved when retrieving complex information within an organization called \"X Systems\"(a stealth mode company) by using a RAG-based chatbot compared to traditional search methods. We compare the information retrieval time using standard search techniques versus the RAG-based chatbot for the same queries. Our results conclude that RAG-based chatbots not only save time in information retrieval but also optimize the search process effectively. This survey was conducted with a sample of 105 employees across departments, average time spending on information retrieval per query was taken as metric. Comparison shows us, there are average 80-95% improvement on search when use RAG based chatbot than using standard search.","short_abstract":"Retrieval-Augmented Generation (RAG) based chatbots are not only useful for information retrieval through questionanswering but also for making complex decisions based on injected private data.we present a survey on how much search time can be saved when retrieving complex information within an organization called \"X S...","url_abs":"https://arxiv.org/abs/2601.07838","url_pdf":"https://arxiv.org/pdf/2601.07838v1","authors":"[\"Jinesh Patel\",\"Arpit Malhotra\",\"Ajay Pande\",\"Prateek Caire\"]","published":"2025-11-10T22:39:26Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"RAG\",\"Generative Adversarial Network\"]","has_code":false}