Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 7 of 7 for “"LeetCode"”.
-
Are Bigger LLMs Always Better? A Study of Open and Closed-Source Models in Code Generation and Translation
… 2, and Llama-3.1, using a curated dataset of LeetCode solutions. Problems were selected across three difficulty levels (easy, medium, and hard), with solutions randomly sourced from Github and verified on the LeetCode platform. Our investigation assesses the feasibility and cost-effectiveness …
-
Large Language Models for Code Generation and Program Comprehension: Exploring Capabilities, Context, and Developer Adaptation
… competitive programming platforms, including LeetCode, Codeforces, and HackerRank. Using 224 problems spanning 15 categories, we compare three conversational LLMs, ChatGPT, Gemini, and Meta AI, against human programmers. Results show that LLMs achieved a 71.43% success rate on structured …
-
Energy Efficiency of AI Generated Code
… LLMs. We use EFFIBENCH dataset containing 1000 LeetCode problems with the most efficient solutions known as canonical solutions. Our research aims to determine which models provide not only functionally correct but also energy-efficient code, thus contributing to more sustainable software …
-
Specialization Project Final Report: Digital Nudge Chat Bot
… as Google Doc, and solving coding problems on LeetCode where people - mostly software engineers - practice interview questions for software engineer positions. We have developed three different bots for these three particular activities. These bots will have interactions with users and send …
-
Helping job seekers prepare for technical interviews by enabling context-rich interview feedback
… Although there are open platforms like Leetcode that allow job seekers to practice their technical proficiency, resources for conducting mock interviews to practice soft skills like communication are limited and costly to interviewees. To address this, we investigated how professional …
-
An Exploratory Study on the Roles of LLMs in Code Similarity Detection and Generation
… NiCad for clone detection. Evaluations on the LeetCode and GPTCloneBench datasets showed that Lang2Clone achieved recall rates of 80% and 85%, respectively, with a precision of 95%. Notably, Lang2Clone outperformed state-of-the-art tools like GraphCodeBERT and CLCDSA in cross-language clone …
-
Understanding the Preparation Phase of Technical Interviews
Technical coding interviews are a core part of the evaluation process of software engineering (SWE) applicants. This process requires SWE job seekers to typically complete either one or multiple rounds of such interviews which are designed to measure their technical understanding of software …