arXiv subjects

Md. Mostafizer Rahman

Publications and source records attributed to Md. Mostafizer Rahman.

5 recordsLinked to original sources

arXiv2026

Error Understanding in Program Code: A Systematic Study of LLM-DL Combinations for Multi-label Classification

Programming is a core skill in CS and SE, yet identifying and resolving code errors remains challenging for practitioners. LLMs have shown remarkable capabilities in NL understanding, but how code-specialized LLMs behave when paired with DL sequence decoders, and which component of such a pipeline drives performance, remains insufficiently explored. This study presents a systematic evaluation of LLM-DL combinations for multi-label error classification (MLEC) of source code. Eight fine-tuned LLMs, including CodeT5, GraphCodeBERT, CodeT5+, UniXcoder, RoBERTa, RoBERTa with a narrowed learning-rate range, PLBART, and CoTexT, are integrated with GRU, LSTM, BiLSTM, and BiLSTM with an additive attention mechanism decoder on a real-world Python code error dataset. The resulting 32 model variants, tuned with Optuna, are assessed on a comprehensive multi-label metric suite. In single-run evaluation, CodeT5+ GRU performs best, with a weighted F1-score of 0.8243, average accuracy of 91.84%, exact match accuracy of 53.78%, Hamming loss of 0.0816, and one-error of 0.0708. To identify where this performance originates, seed-controlled baselines and component ablations are added with paired significance testing. Encoder choice has the largest effect: across four encoders sharing an identical linear classification head, the weighted F1-score spans 0.7846 to 0.8263, ordered by code specialization. On CodeT5+, the linear head exceeds the GRU hybrid under matched seeds by 0.0040 weighted F1 (p = 0.0013) while training about 24% faster. Max pooling outperforms mean and attention pooling, and explicitly modeling label interactions does not improve weighted F1 despite substantial label co-occurrence. These results identify encoder quality, rather than decoder complexity, as the primary lever for MLEC and support the development of scalable automated feedback tools for programming education and SE.

cs.SE↗

arXiv2025

Code Refactoring with LLM: A Comprehensive Evaluation With Few-Shot Settings

In today's world, the focus of programmers has shifted from writing complex, error-prone code to prioritizing simple, clear, efficient, and sustainable code that makes programs easier to understand. Code refactoring plays a critical role in this transition by improving structural organization and optimizing performance. However, existing refactoring methods are limited in their ability to generalize across multiple programming languages and coding styles, as they often rely on manually crafted transformation rules. The objectives of this study are to (i) develop an Large Language Models (LLMs)-based framework capable of performing accurate and efficient code refactoring across multiple languages (C, C++, C#, Python, Java), (ii) investigate the impact of prompt engineering (Temperature, Different shot algorithm) and instruction fine-tuning on refactoring effectiveness, and (iii) evaluate the quality improvements (Compilability, Correctness, Distance, Similarity, Number of Lines, Token, Character, Cyclomatic Complexity) in refactored code through empirical metrics and human assessment. To accomplish these goals, we propose a fine-tuned prompt-engineering-based model combined with few-shot learning for multilingual code refactoring. Experimental results indicate that Java achieves the highest overall correctness up to 99.99% the 10-shot setting, records the highest average compilability of 94.78% compared to the original source code and maintains high similarity (Approx. 53-54%) and thus demonstrates a strong balance between structural modifications and semantic preservation. Python exhibits the lowest structural distance across all shots (Approx. 277-294) while achieving moderate similarity ( Approx. 44-48%) that indicates consistent and minimally disruptive refactoring.

cs.SE↗

arXiv2025

RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis

Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder the process of sentiment analysis including the lexical diversity exhibited in comments, the presence of long dependencies within the text, encountering unknown symbols and words, and dealing with imbalanced datasets. Moreover, existing sentiment analysis tasks mostly leveraged sequential models to encode the long dependent texts and it requires longer execution time as it processes the text sequentially. In contrast, the Transformer requires less execution time due to its parallel processing nature. In this work, we introduce a novel hybrid deep learning model, RoBERTa-BiLSTM, which combines the Robustly Optimized BERT Pretraining Approach (RoBERTa) with Bidirectional Long Short-Term Memory (BiLSTM) networks. RoBERTa is utilized to generate meaningful word embedding vectors, while BiLSTM effectively captures the contextual semantics of long-dependent texts. The RoBERTa-BiLSTM hybrid model leverages the strengths of both sequential and Transformer models to enhance performance in sentiment analysis. We conducted experiments using datasets from IMDb, Twitter US Airline, and Sentiment140 to evaluate the proposed model against existing state-of-the-art methods. Our experimental findings demonstrate that the RoBERTa-BiLSTM model surpasses baseline models (e.g., BERT, RoBERTa-base, RoBERTa-GRU, and RoBERTa-LSTM), achieving accuracies of 80.74%, 92.36%, and 82.25% on the Twitter US Airline, IMDb, and Sentiment140 datasets, respectively. Additionally, the model achieves F1-scores of 80.73%, 92.35%, and 82.25% on the same datasets, respectively.

cs.CL↗

arXiv2023

Program Repair with Minimal Edits Using CodeT5

Programmers often struggle to identify and fix bugs in their programs. In recent years, many language models (LMs) have been proposed to fix erroneous programs and support error recovery. However, the LMs tend to generate solutions that differ from the original input programs. This leads to potential comprehension difficulties for users. In this paper, we propose an approach to suggest a correct program with minimal repair edits using CodeT5. We fine-tune a pre-trained CodeT5 on code pairs of wrong and correct programs and evaluate its performance with several baseline models. The experimental results show that the fine-tuned CodeT5 achieves a pass@100 of 91.95% and an average edit distance of the most similar correct program of 6.84, which indicates that at least one correct program can be suggested by generating 100 candidate programs. We demonstrate the effectiveness of LMs in suggesting program repair with minimal edits for solving introductory programming problems.

cs.CL↗

arXiv2023

Exploring Automated Code Evaluation Systems and Resources for Code Analysis: A Comprehensive Survey

The automated code evaluation system (AES) is mainly designed to reliably assess user-submitted code. Due to their extensive range of applications and the accumulation of valuable resources, AESs are becoming increasingly popular. Research on the application of AES and their real-world resource exploration for diverse coding tasks is still lacking. In this study, we conducted a comprehensive survey on AESs and their resources. This survey explores the application areas of AESs, available resources, and resource utilization for coding tasks. AESs are categorized into programming contests, programming learning and education, recruitment, online compilers, and additional modules, depending on their application. We explore the available datasets and other resources of these systems for research, analysis, and coding tasks. Moreover, we provide an overview of machine learning-driven coding tasks, such as bug detection, code review, comprehension, refactoring, search, representation, and repair. These tasks are performed using real-life datasets. In addition, we briefly discuss the Aizu Online Judge platform as a real example of an AES from the perspectives of system design (hardware and software), operation (competition and education), and research. This is due to the scalability of the AOJ platform (programming education, competitions, and practice), open internal features (hardware and software), attention from the research community, open source data (e.g., solution codes and submission documents), and transparency. We also analyze the overall performance of this system and the perceived challenges over the years.

cs.SE↗