Anupam Purwar

Mr. Anupam Purwar


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 October 2023
Verified
Conference Paper
Open access
APAnupam Purwar
Anupam Purwar
RSRahul Sundar
Rahul Sundar
Retrieving answers in a quick and low cost manner without hallucinations from a combination of structured and unstructured data using Language models is a major hurdle. This is what prevents employment of Language models in knowledge retrieval automation. This becomes accentuated when one wants to integrate a speech interface on top of a text based knowledge retrieval system. Besides, for commercial search and chat-bot applications, complete reliance on commercial large language models (LLMs) like GPT 3.5 etc. can be very costly. In the present study, the authors have addressed the aforementioned problem by first developing a keyword based search framework which augments discovery of the context from the document to be provided to the LLM. The keywords in turn are generated by a relatively smaller LLM and cached for comparison with keywords generated by the same smaller LLM against the query raised. This significantly reduces time and cost to find the context within documents. Once the context is set, a larger LLM uses that to provide answers based on a prompt tailored for Q&A. This research work demonstrates that use of keywords in context identification reduces the overall inference time and cost of information retrieval. Given this reduction in inference time and cost with the keyword augmented retrieval framework, a speech based interface for user input and response readout was integrated. This allowed a seamless interaction with the language model.

1 September 2014 in Egyptian Journal of Forensic Sciences
Verified
Journal Article
Open access
SKShally Khanna
Shally Khanna
APAnupam Purwar
Anupam Purwar
NSNarendra Nath Singh
Narendra Nath Singh
VAVarun Arora
Varun Arora
ASAmit Singh
Amit Singh
SWSaurabh Wahi
Saurabh Wahi
A number of methods have been introduced in scientific literature to study the lip print and palatal rugae; still there is a need for more descriptive and self-explanatory methods. Awareness regarding practical knowledge of cheiloscopy and palatoscopy is ambiguous among dental professionals. In the present work, an effort was made to introduce an educational training module for dental professionals with a view to improving the data recording and interpretation methods. A computer aided statistical method has also been suggested, i.e., systematic stage-wise filtering to test the uniqueness of lip and palatal rugae patterns. In this study, dental professionals were asked to match random lip and palatal rugae patterns before and after training. Proportions of accurate matching pre- and post-training were then compared. A systematic stage-wise filtering method was used to prove the uniqueness of lip prints and palatal rugae in large samples. It was observed that the educational training module helped to improve the ability of dental professionals in identifying individuals based on lip prints and palatal rugae. Application of systematic stage-wise filtering technique eased the process of checking the uniqueness of patterns

19 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
CHChitranshu Harbola
Chitranshu Harbola
APAnupam Purwar
Anupam Purwar
LLMs are well known for their ability to retrieve knowledge from data sources and generate text at scale taking benefit from their Decoder based architecture; however, their capability to handle long, numerically intensive telemetry datasets remains largely unexplored. In this paper, we study the behavior of LLMs in the analysis of industrial machinery telemetry to explore their ability to identify patterns in bearing vibration datasets. For the vibration data, characteristic frequency metrics have been derived using classical physics-based formulas, and synthetic anomalies have been introduced through controlled signal perturbations. Anomaly detection in industrial machinery telemetry is essential for early fault identification and predictive maintenance across a wide range of equipment types. In our experiments, LLMs demonstrated varying performance depending on the model's capabilities in reasoning and mathematical tasks. We benchmarked LLMs' performance against established machine learning models. Since machine learning (ML) models are based on numerical computations and loss function minimization, they are generally expected to perform better in detecting anomalies. However, in our experiments, we observed that LLMs, when asked for multishot serialized telemetry data, matched the precision and recall of traditional ML models and, in some cases, exceeded the accuracy by up to 9.09%. We propose an LLM-aided machine prognosis (LAMP) framework, to utilize the growing capability of LLMs for analysis of complex machinery telemetry dataset using conversational natural language.