Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM60741
Volume:
10 |
4 |
April 2026
Pages:
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
India faces an acute problem of legal accessibility, with about 2 lawyers per 1000 people. Complicated legal jargon, expensive consultation fees, and lack of knowledge hinder many people from seeking justice. Pocket Specter is a specialized domain AI SaaS platform that tries to fill the void by using a Retrieval Augmentation Generation mechanism. The Pocket Specter software includes legal chatbot based on AI technology and intelligent document analysis in the fields of consumer, labour, and family laws. Pocket Specter uses BGE-M3 embeddings in combination with PostgreSQL pgvector technology with a large language model to base their responses on legal documents, minimizing hallucinations. In addition, the document analysis tool analyzes and highlights important information about responsibilities and potential risks in uploaded documents in .pdf/.docx formats. According to experiment results, Pocket Specter is more than 75% relevant in legal responses in comparison with simple LLM methods.
KEYWORDS
Publication Date
4/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...