{
  "annotation_id": "28785b61-622c-4073-9af2-94d0d00a9a24",
  "date_created": "2026-02-17T05:53:12.593000Z",
  "date_modified": "2026-02-17T05:53:12.593000Z",
  "file_hash": "161b0f56b367e5697bb783be831b55bac14c1f030c7f5175e5eb3deef90e620c",
  "private": false,
  "record": {
    "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.",
    "arxiv_id": "2601.07838",
    "authors": [
      "Jinesh Patel",
      "Arpit Malhotra",
      "Ajay Pande",
      "Prateek Caire"
    ],
    "categories": [
      "cs.IR",
      "cs.AI"
    ],
    "doi": "10.36106/paripex/5005979",
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "A survey: Information search time optimization based on RAG (Retrieval Augmentation Generation) chatbot",
    "url": "https://arxiv.org/abs/2601.07838",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "b1bde439-299f-401f-a9ef-523f9c952dd0",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}