Richa Sharma

Dr. Richa Sharma

University of Delhi, India

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 December 2013 in Ceramics International
Verified
Journal Article
Closed access
PPPoonam Pahuja
Poonam Pahuja
RSRicha Sharma
Richa Sharma
CPChandra Prakash
Chandra Prakash
RTR.P. Tandon
R.P. Tandon

1 June 2024 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
AKAnkit Kumar
Ankit Kumar
RSRicha Sharma
Richa Sharma
PBPunam Bedi
Punam Bedi
This study carries out a comprehensive comparison of fine-tuned GPT models (GPT-2, GPT-3, GPT-3.5) and LLaMA-2 models (LLaMA-2 7B, LLaMA-2 13B, LLaMA-2 70B) in text classification, addressing dataset sizes, model scales, and task diversity. Since its inception in 2018, the GPT series has been pivotal in advancing NLP, with each iteration introducing substantial enhancements. Despite its progress, detailed analyses, especially against competitive open-source models like the LLaMA-2 series in text classification, remain scarce. The current study fills this gap by fine-tuning these models across varied datasets, focusing on enhancing task-specific performance in hate speech and offensive language detection, fake news classification, and sentiment analysis. The learning efficacy and efficiency of the GPT and LLaMA-2 models were evaluated, providing a nuanced guide to choosing optimal models for NLP tasks based on architectural benefits and adaptation efficiency with limited data and resources. In particular, even with datasets as small as 1,000 rows per class, the F1 scores for the GPT-3.5 and LLaMA-2 models exceeded 0.9, reaching 0.99 with complete datasets. Additionally, the LLaMA-2 13B and 70B models outperformed GPT-3, demonstrating their superior efficiency and effectiveness in text classification. Both the GPT and LLaMA-2 series showed commendable performance on all three tasks, underscoring their ability to handle a diversity of tasks. Based on the size, performance, and resources required for fine-tuning the model, this study identifies LLaMA-2 13B as the most optimal model for NLP tasks.

31 May 2014 in International Journal in Foundations of Computer Science & Technology
Verified
Journal Article
Open access
RSRicha Sharma
Richa Sharma
SNShweta Nigam
Shweta Nigam
RJRekha Jain
Rekha Jain

31 March 2014 in International Journal in Foundations of Computer Science & Technology
Verified
Journal Article
Open access
RSRicha Sharma
Richa Sharma
SNShweta Nigam
Shweta Nigam
RJRekha Jain
Rekha Jain

23 April 2015 in Journal of Materials Science: Materials in Electronics
Verified
Journal Article
Closed access
PDF file
RSRicha Sharma
Richa Sharma
RTR. P. Tandon
R. P. Tandon

4 March 2024 in Journal of Classification
Verified
Journal Article
Closed access
PDF file
HBHema Banati
Hema Banati
RSRicha Sharma
Richa Sharma
AYAsha Yadav
Asha Yadav