http://repository.iiitd.edu.in/xmlui/handle/123456789/45 2026-04-11T13:08:42Z 2026-04-11T13:08:42Z Arora, Utkarsh Arora, Gaurav (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1760 2025-07-02T22:00:23Z 2023-12-12T00:00:00Z

Analysis of the impacts of MGNREGA using spatial data analysis Arora, Utkarsh; Arora, Gaurav (Advisor) In response to the escalating global demand for secure access to freshwater resources, governments worldwide have implemented technology-driven initiatives for water resource development. This research focuses on a pivotal initiative, the Mahatma Gandhi National Rural Employment Guarantee Act (MGNREGA) of 2005, which has been instrumental in constructing water conservation structures and other assets in rural areas to enhance community welfare and generate employment opportunities. Under the program, over 120 million assets have been constructed across India over the course of seventeen years since the initiative was first announced. There exists a knowledge gap regarding the evaluation of the investment returns derived from the construction of water conservation assets, limiting the ability of policymakers in the Ministry of Rural Development (MoRD). This study aims to bridge this gap, by leveraging various geospatial technology and datasets. For the analysis, diverse spatially delineated data sources from across the country and over different years have been collected and integrated. To facilitate this, a robust data warehouse has been developed, utilizing concepts of computer networks and parallelization for dataset extraction, along with natural language processing (NLP) for seamless integration. The study employs a combination of spatial data analysis, econometrics, and machine learning techniques to investigate the factors influencing the construction of Farm Ponds in specific locations, addressing the questions of where, when, why, and how long these constructions occur. Commencing with an in-depth analysis of the state of Uttar Pradesh, the scope of the study expands to encompass the entirety of India.

2023-12-12T00:00:00Z Mittal, Shefali Prince, Deepak (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1757 2025-06-23T22:00:51Z 2024-04-29T00:00:00Z

Grief unveiled: insights into the emotional terrain of college life Mittal, Shefali; Prince, Deepak (Advisor) This project investigates the intersection of grief, academic performance, and coping mechanisms among college students. Through thorough research of scholarly papers and influential books, it reveals the complexity of grief experiences within higher education. The study uncovers diverse coping strategies employed by individuals managing grief while balancing academic responsibilities. It highlights the profound impact of grief on academic outcomes, advocating for tailored support systems in colleges and universities. Recommendations are provided for implementing grief support programs, flexible academic policies, and awareness initiatives. By prioritizing the well-being of grieving students, institutions can foster resilience and academic success. This project urges stakeholders to recognize and address the unique needs of grieving college students, promoting compassion and proactive support measures.

2024-04-29T00:00:00Z Bhatia, Shreya Gandhi, Tarushi Jalote, Pankaj (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1756 2025-06-23T22:00:51Z 2024-04-29T00:00:00Z

Test case design generation from SRS using LLMs Bhatia, Shreya; Gandhi, Tarushi; Jalote, Pankaj (Advisor) System testing is a crucial phase in software development, ensuring that the final product meets specified requirements and functions correctly. However, creating comprehensive test cases for system testing can be challenging and time-consuming. This paper explores the use of Large Language Models (LLMs) for generating test case designs from Software Requirements Specification (SRS) documents. With the assistance of LLMs, software engineers can save time and effort while ensuring thorough test coverage. In this study, we collected a dataset consisting of five SRS documents from student engineering projects containing both functional and non-functional requirements. We focused on the functional requirements section, particularly the use cases, as the basis for generating test-case designs. Using prompts, we instructed the LLM first to familiarize itself with the SRS and then generate test case designs for each use case. Subsequently, we evaluated the quality of the generated test cases through feedback from the students who authored the SRS documents. Our experimental design allows us to address several research questions, including the effectiveness of LLMs in generating useful and non-redundanttest case designs, the identification of missing test case conditions, and the nature of use cases where LLMs may struggle to provide adequate test coverage. Through this research, we aim to streamline the system testing process and improve the overall quality of software products.

2024-04-29T00:00:00Z Dixit, Shantanu Akhtar, Md Shad (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1755 2025-06-23T22:00:51Z 2023-11-29T00:00:00Z

Collaborative and cross-modal distillation for large language models Dixit, Shantanu; Akhtar, Md Shad (Advisor) Knowledge distillation is a technique that involves transferring knowledge from a larger teacher model to a smaller student model. The latest developments in meta-learning-based knowledge distillation emphasize the significance of fine-tuning the teacher models while taking into account the student’s need for better knowledge distillation. Nevertheless, current MetaKD methods frequently fail to provide incentives for the teacher model to improve itself. We introduce a meta-policy distillation technique aiming to foster both collaboration and competition during the fine-tuning of the teacher model within the meta-learning phase. Additionally, we put forth a curriculum learning framework tailored for the student model within a competitive setting. In this context, the student model endeavors to surpass the teacher model through self-training on a diverse range of tasks. We conduct extensive experiments on two NLU benchmarks GLUE andSuperGLUE [74, 75] and validate our methodology’s effectiveness against various KD techniques.As an extension to the above work we further explore the setting where teacher-student modalities differ (ex: text-vision and vice-versa). Existing cross-modal distillation approaches predominantly utilize modality-dependent features for knowledge distillation, and therefore, fail to adaptively learn the abstractions in different modalities. we propose a generic and modality-agnostic cross-modal distillation technique that can distil knowledge from any arbitrary cross-modal open or closed teacher model to any arbitrary student model in any different modality. Our empirical studies encompass eight natural language understanding tasks and an image classification task, showcasing the efficacy of cross-modal distillation in enhancing the performance of student models.

2023-11-29T00:00:00Z