GovGuideBot: LLM for Government Document Assistance

DOI

10.2991/978-94-6239-678-4_38How to use a DOI?

Keywords

AI Chatbot; Named Entity Recognition; JavaScript Object Notation; Large Language Model; Application programming interface

Abstract

Millions of people it is very difficult to apply for important government documents like income certificates, caste certificates, and proof of domicile, especially if they live in rural areas or have limited digital skills in India. Dispersed portals, unclear instructions, inconsistent state-by-state procedures, and districtlevel these all factors complicate the process. These problems often result in process errors, frequent office visits, and the exclusion of less technical expertized individuals. GovGuideBot has been developed, an AI Chatbot, Large Language Model(LLM) that explains government documentation procedures, to address this issue. It provides easy-to-use, locationbased, step-by-step assistance. In order to understand user intent, the system uses a Named Entity Recognition(NLP) pipeline that is optimized with transformer models like. Named Entity Recognition (NER) is used to identify crucial information such as document type, state, and district. These specifics are arranged in structured JavaScript Object Notation (JSON) workflows that enable region specific instructions. GovGuideBot also uses location entered by user query to adapt procedures for user locations, links to official government websites to guarantee accuracy, and uses the YouTube DataApplication programming interface (API) to offer visual tutorials which are particularly useful for users who might have literacy issues or are using these services for the first time. With a precision of 91%, a recall of 93%, and an overall F1-score of 92% for identifying intents and entities, GovGuideBot performs well when tested on actual citizen questions. About half of the planned features were successfully implemented in the working prototype we created for Maharashtra, which includes work-flows for income, caste, and domicile certificates.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Arti Patle
AU  - Deepika Ajalkar
AU  - Siddhika Jadhav
AU  - Shital Undalkar
AU  - Tousif Tamboli
PY  - 2026
DA  - 2026/05/28
TI  - GovGuideBot: LLM for Government Document Assistance
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 477
EP  - 489
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_38
DO  - 10.2991/978-94-6239-678-4_38
ID  - Patle2026
ER  -