Sawan Rai
Research Subjects
Sawan Rai has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Atul Gupta
Computer Science and Engineering, PDPM Indian Institute of Information Technology, Design and Manufacturing (IIITDM), Jabalpur, MP, India, Jabalpur, Madhya Pradesh, India
6 shared publications - Ramesh Chandra Belwal
Department of Computer Science and Engineering, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, India
5 shared publications - Davuluri Bhanu Prakash
Department of Computer Science and Engineering, SRM University AP, Amaravati, INDIA
1 shared publication - Paras Tiwari
Department of Computer Science and Engineering, IIT (BHU), Varanasi, India
1 shared publication Ramesh Chandra Belwal
PDPM Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Jabalpur, India
1 shared publication
Latest Publications
- 24 October 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (8) , 823
Automatic Mapping of Course Learning Outcome and Program Learning Outcome in Outcome-Based Education
- 24 October 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (8) , 823
Automatic Mapping of Course Learning Outcome and Program Learning Outcome in Outcome-Based Education
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 293-308
The Ethical and Regulatory Landscape of Large Language Models
Large Language Models (LLMs) are transforming industries by enabling advanced natural language processing (NLP) applications, yet their adoption raises ethical and regulatory concerns. Bias in training data can lead to unfair outcomes in hiring, credit scoring, and legal decisions, necessitating bias mitigation techniques such as debiasing algorithms and diverse data curation. Privacy risks arise from LLMs memorizing sensitive data, requiring compliance with regulations like GDPR and CCPA through differential privacy and encryption-based training. The opacity of LLMs challenges trust, prompting research in Explainable AI (XAI) methods like SHAP and LIME. Governments and industry leaders are shaping AI regulations, such as the EU AI Act, to balance innovation with responsibility. Future AI governance will require interdisciplinary collaboration, ethical auditing, and continuous oversight. Ensuring fairness, transparency, and accountability will be key to responsible AI deployment, enabling organizations to leverage LLMs' potential while minimizing risks.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 293-308
The Ethical and Regulatory Landscape of Large Language Models
Large Language Models (LLMs) are transforming industries by enabling advanced natural language processing (NLP) applications, yet their adoption raises ethical and regulatory concerns. Bias in training data can lead to unfair outcomes in hiring, credit scoring, and legal decisions, necessitating bias mitigation techniques such as debiasing algorithms and diverse data curation. Privacy risks arise from LLMs memorizing sensitive data, requiring compliance with regulations like GDPR and CCPA through differential privacy and encryption-based training. The opacity of LLMs challenges trust, prompting research in Explainable AI (XAI) methods like SHAP and LIME. Governments and industry leaders are shaping AI regulations, such as the EU AI Act, to balance innovation with responsibility. Future AI governance will require interdisciplinary collaboration, ethical auditing, and continuous oversight. Ensuring fairness, transparency, and accountability will be key to responsible AI deployment, enabling organizations to leverage LLMs' potential while minimizing risks.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 255-270
The Ethical and Regulatory Landscape of Large Language Models
Large Language Models (LLMs) are transforming industries by enabling advanced natural language processing (NLP) applications, yet their adoption raises ethical and regulatory concerns. Bias in training data can lead to unfair outcomes in hiring, credit scoring, and legal decisions, necessitating bias mitigation techniques such as debiasing algorithms and diverse data curation. Privacy risks arise from LLMs memorizing sensitive data, requiring compliance with regulations like GDPR and CCPA through differential privacy and encryption-based training. The opacity of LLMs challenges trust, prompting research in Explainable AI (XAI) methods like SHAP and LIME. Governments and industry leaders are shaping AI regulations, such as the EU AI Act, to balance innovation with responsibility. Future AI governance will require interdisciplinary collaboration, ethical auditing, and continuous oversight. Ensuring fairness, transparency, and accountability will be key to responsible AI deployment, enabling organizations to leverage LLMs' potential while minimizing risks.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 255-270
The Ethical and Regulatory Landscape of Large Language Models
Large Language Models (LLMs) are transforming industries by enabling advanced natural language processing (NLP) applications, yet their adoption raises ethical and regulatory concerns. Bias in training data can lead to unfair outcomes in hiring, credit scoring, and legal decisions, necessitating bias mitigation techniques such as debiasing algorithms and diverse data curation. Privacy risks arise from LLMs memorizing sensitive data, requiring compliance with regulations like GDPR and CCPA through differential privacy and encryption-based training. The opacity of LLMs challenges trust, prompting research in Explainable AI (XAI) methods like SHAP and LIME. Governments and industry leaders are shaping AI regulations, such as the EU AI Act, to balance innovation with responsibility. Future AI governance will require interdisciplinary collaboration, ethical auditing, and continuous oversight. Ensuring fairness, transparency, and accountability will be key to responsible AI deployment, enabling organizations to leverage LLMs' potential while minimizing risks.
- 19 July 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 48 (2) , 1845-1858
Is the Corpus Ready for Machine Translation? A Case Study with Python to Pseudo-Code Corpus
The availability of data is the driving force behind most of the state-of-the-art techniques for machine translation tasks. Understandably, this availability of data motivates researchers to propose new techniques and claim about the superiority of their techniques over the existing ones by using suitable evaluation measures. However, the performance of underlying learning algorithms can be greatly influenced by the correctness and the consistency of the corpus. We present our investigations for the relevance of a publicly available python to pseudo-code parallel corpus for automated documentation task, and the studies performed using this corpus. We found that the corpus had many visible issues like overlapping of instances, inconsistency in translation styles, incompleteness, and misspelled words. We show that these discrepancies can significantly influence the performance of the learning algorithms to the extent that they could have caused previous studies to draw incorrect conclusions. We performed our experimental study using statistical machine translation and neural machine translation models. We have recorded a significant difference (\(\sim \) 10% on BLEU score) in the models’ performance after removing the issues from the corpus.- 19 July 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 48 (2) , 1845-1858
Is the Corpus Ready for Machine Translation? A Case Study with Python to Pseudo-Code Corpus
The availability of data is the driving force behind most of the state-of-the-art techniques for machine translation tasks. Understandably, this availability of data motivates researchers to propose new techniques and claim about the superiority of their techniques over the existing ones by using suitable evaluation measures. However, the performance of underlying learning algorithms can be greatly influenced by the correctness and the consistency of the corpus. We present our investigations for the relevance of a publicly available python to pseudo-code parallel corpus for automated documentation task, and the studies performed using this corpus. We found that the corpus had many visible issues like overlapping of instances, inconsistency in translation styles, incompleteness, and misspelled words. We show that these discrepancies can significantly influence the performance of the learning algorithms to the extent that they could have caused previous studies to draw incorrect conclusions. We performed our experimental study using statistical machine translation and neural machine translation models. We have recorded a significant difference (\(\sim \) 10% on BLEU score) in the models’ performance after removing the issues from the corpus.- Open Access
- 21 June 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 13 (5) , 1-44
A Review on Source Code Documentation
Context: Coding is an incremental activity where a developer may need to understand a code before making suitable changes in the code. Code documentation is considered one of the best practices in software development but requires significant efforts from developers. Recent advances in natural language processing and machine learning have provided enough motivation to devise automated approaches for source code documentation at multiple levels. Objective: The review aims to study current code documentation practices and analyze the existing literature to provide a perspective on their preparedness to address the stated problem and the challenges that lie ahead. Methodology: We provide a detailed account of the literature in the area of automated source code documentation at different levels and critically analyze the effectiveness of the proposed approaches. This also allows us to infer gaps and challenges to address the problem at different levels. Findings: (1) The research community focused on method-level summarization. (2) Deep learning has dominated the past five years of this research field. (3) Researchers are regularly proposing bigger corpora for source code documentation. (4) Java and Python are the widely used programming languages as corpus. (5) Bilingual Evaluation Understudy is the most favored evaluation metric for the research persons.
- 21 June 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 13 (5) , 1-44
Open AccessA Review on Source Code Documentation
Context: Coding is an incremental activity where a developer may need to understand a code before making suitable changes in the code. Code documentation is considered one of the best practices in software development but requires significant efforts from developers. Recent advances in natural language processing and machine learning have provided enough motivation to devise automated approaches for source code documentation at multiple levels. Objective: The review aims to study current code documentation practices and analyze the existing literature to provide a perspective on their preparedness to address the stated problem and the challenges that lie ahead. Methodology: We provide a detailed account of the literature in the area of automated source code documentation at different levels and critically analyze the effectiveness of the proposed approaches. This also allows us to infer gaps and challenges to address the problem at different levels. Findings: (1) The research community focused on method-level summarization. (2) Deep learning has dominated the past five years of this research field. (3) Researchers are regularly proposing bigger corpora for source code documentation. (4) Java and Python are the widely used programming languages as corpus. (5) Bilingual Evaluation Understudy is the most favored evaluation metric for the research persons.
- 22 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 199
Generating class name in sequential manner using convolution attention neural network
- 22 March 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 199
Generating class name in sequential manner using convolution attention neural network
- 2 February 2022
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (9) , 11531-11543
Accurate module name prediction using similarity based and sequence generation models
- 2 February 2022
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (9) , 11531-11543
Accurate module name prediction using similarity based and sequence generation models
- 12 September 2021
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 47 (2) , 2141-2157
Effect of Identifier Tokenization on Automatic Source Code Documentation
- 12 September 2021
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 47 (2) , 2141-2157
Effect of Identifier Tokenization on Automatic Source Code Documentation
- 17 October 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 12 (10) , 8975-8990
A new graph-based extractive text summarization using keywords or topic modeling
- 17 October 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 12 (10) , 8975-8990
A new graph-based extractive text summarization using keywords or topic modeling