3 papers
cs.CR2026
Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback
Vidyut Sriram, Sawan Pandita, Achintya Lakshmanan +2
Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs bene…
cs.CY2024
How Decentralization Affects User Agency on Social Platforms
Aditya Surve, Aneesh Shamraj, Swapneel Mehta
Mainstream social media platforms function as "walled garden" ecosystems that restrict user agency, control, and data portability. They have demonstrated a lack of transparency tha…
cs.CL2024
Cross-Language Assessment of Mathematical Capability of ChatGPT
Gargi Sathe, Aneesh Shamraj, Aditya Surve +2
This paper presents an evaluation of the mathematical capability of ChatGPT across diverse languages like Hindi, Gujarati, and Marathi. ChatGPT, based on GPT-3.5 by OpenAI, has gar…