K Vimal Kumar

Dr. K Vimal Kumar

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
29 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AJArti Jain
Arti Jain
AAAnuja Arora
Anuja Arora
JORGE LUIS MORATO LARAJORGE LUIS MORATO LARA
JORGE LUIS MORATO LARA
DYDivakar Yadav
Divakar Yadav
KKK Vimal Kumar
K Vimal Kumar
In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the ever-growing volume of text data available online to discover relevant information faster. In this research, the ATS methodology is proposed for the Hindi language using Real Coded Genetic Algorithm (RCGA) over the health corpus, available in the Kaggle dataset. The methodology comprises five phases: preprocessing, feature extraction, processing, sentence ranking, and summary generation. Rigorous experimentation on varied feature sets is performed where distinguishing features, namely- sentence similarity and named entity features are combined with others for computing the evaluation metrics. The top 14 feature combinations are evaluated through Recall-Oriented Understudy for Gisting Evaluation (ROUGE) measure. RCGA computes appropriate feature weights through strings of features, chromosomes selection, and reproduction operators: Simulating Binary Crossover and Polynomial Mutation. To extract the highest scored sentences as the corpus summary, different compression rates are tested. In comparison with existing summarization tools, the ATS extractive method gives a summary reduction of 65%.


12 July 2026
Verified
Book Chapter
Open access
PDF file
TKTalhat Khan
Talhat Khan
KKK Vimal Kumar
K Vimal Kumar
Conor RyanConor Ryan
Conor Ryan
The computational demands of Large Language Models (LLMs) during inference are primarily determined by response length. A substantial portion of the computational cost of LLM inference arises from unnecessary autoregressive decoding, where models generate verbose explanations from simple prompts even when simple, structured answers are sufficient. We introduce a question-type-aware inference framework for prompt routing to produce compact, token-optimised responses. Our approach employs a lightweight BERT classifier to assign incoming queries to predefined question types (e.g., yes/no/maybe, multiple-choice, or descriptive). Each query is then routed to a specialised prompt template designed for concise response generation. We tested our framework on factual tasks (yes/no/maybe and multiple-choice) to ensure rigorous accuracy verification. The methodology is validated across three medical benchmark using four LLMs with 8–70 billion parameters. Results demonstrate a substantial decrease in both average token counts and floating-point operations (FLOPs), achieving peak savings of 99.4%, while maintaining baseline accuracy. This approach offers a scalable solution to lower the operational costs of deploying LLMs in specialized, knowledge-intensive domains.

2 July 2026
Verified
Book Chapter
Closed access
PDF file
KKK Vimal Kumar
K Vimal Kumar
GVGauri Vaidya
Gauri Vaidya
DLDeepankur Lohiya
Deepankur Lohiya
Conor RyanConor Ryan
Conor Ryan
MKMeghana Kshirsagar
Meghana Kshirsagar

26 September 2023
Verified
Book Chapter
Closed access
PDF file
KKK Vimal Kumar
K Vimal Kumar
PPPritee Parwekar
Pritee Parwekar
GGGunjan Gupta
Gunjan Gupta

4 July 2022
Verified
Book Chapter
Closed access
PDF file
KKK Vimal Kumar
K Vimal Kumar
SAShruti Ahuja
Shruti Ahuja
SCSkandha Choudary
Skandha Choudary
PPPritee Parwekar
Pritee Parwekar