BPBalázs Pintér

Balázs Pintér

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Balázs Pintér has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Investigating the Refactoring Capabilities of Small Open-Weight Language Models

    by Tamás Márton, Balázs Szalontai, Balázs Pintér, Tibor Gregorics

    Refactoring is essential for developing maintainable software. Using Large Language Models in software engineering is widespread, but compared to well-established domains such as code generation, reliable refactoring is still relatively underexplored. In this paper, we perform a broad analysis on the refactoring capabilities of small open-weight language models (SLMs) by evaluating 12 models on 3453 Python programs. Our study focuses on the two defining aspects of refactoring: behavior preservation and code quality improvement. We evaluate these properties using unit tests and various code metrics. Across models ranging from 0.5B to 8 B parameters, most models improve code quality. Larger models are more reliable, as they preserve behavior more consistently. Reasoning models often make more significant changes while refactoring. Allowing models to generate reasoning traces improves performance, but only for models larger than 4B. For smaller models, reasoning in fact reduces refactoring reliability. The difficulty of the underlying task affects refactoring performance, with more complex tasks associated with higher failure rates. Our results indicate that current open SLMs can support refactoring tasks, especially larger ones with reasoning capabilities, but they are best used with human oversight.

  • Open Access

    Investigating the Refactoring Capabilities of Small Open-Weight Language Models

    by Tamás Márton, Balázs Szalontai, Balázs Pintér, Tibor Gregorics

    Refactoring is essential for developing maintainable software. Using Large Language Models in software engineering is widespread, but compared to well-established domains such as code generation, reliable refactoring is still relatively underexplored. In this paper, we perform a broad analysis on the refactoring capabilities of small open-weight language models (SLMs) by evaluating 12 models on 3,453 Python programs. Our study focuses on the two defining aspects of refactoring: behavior preservation and code quality improvement. We evaluate these properties using unit tests and various code metrics. Across models ranging from 0.5B to 8B parameters, most models improve code quality. Larger models are more reliable, as they preserve behavior more consistently. Reasoning models often make more significant changes while refactoring. Allowing models to generate reasoning traces improves performance, but only for models larger than 4B. For smaller models, reasoning in fact reduces refactoring reliability. The difficulty of the underlying task affects refactoring performance, with more complex tasks associated with higher failure rates. Our results indicate that current open SLMs can support refactoring tasks, especially larger ones with reasoning capabilities, but they are best used with human oversight.

  • Open Access

    Investigating Reproducibility Challenges in LLM Bugfixing on the HumanEvalFix Benchmark

    by Balázs Szalontai, Balázs Márton, Balázs Pintér, Tibor Gregorics

    Benchmark results for large language models often show inconsistencies across different studies. This paper investigates the challenges of reproducing these results in automatic bugfixing using LLMs, on the HumanEvalFix benchmark. To determine the cause of the differing results in the literature, we attempted to reproduce a subset of them by evaluating 12 models in the DeepSeekCoder, CodeGemma, CodeLlama, and WizardCoder model families, in different sizes and tunings. A total of 35 unique results were reported for these models across studies, of which we successfully reproduced 12. We identified several relevant factors that influenced the results. The base models can be confused with their instruction-tuned variants, making their results better than expected. Incorrect prompt templates or generation length can decrease benchmark performance, as well as using 4-bit quantization. Using sampling instead of greedy decoding can increase the variance, especially with higher temperature values. We found that precision and 8-bit quantization have less influence on benchmark results.


  • Open Access

    Investigating Reproducibility Challenges in LLM Bugfixing on the HumanEvalFix Benchmark

    by Balázs Szalontai, Balázs Márton, Balázs Pintér, Tibor Gregorics

    Benchmark results for Large Language Models often show inconsistencies across different studies. This paper investigates the challenges of reproducing these results in automatic bugfixing using LLMs, on the HumanEvalFix benchmark. To determine the cause of the differing results in the literature, we attempted to reproduce a subset of them by evaluating 11 models in the DeepSeekCoder, CodeGemma, and CodeLlama model families, in different sizes and tunings. A total of 32 unique results were reported for these models across studies, of which we successfully reproduced 16. We identified several relevant factors that influence the results. Base models can be confused with their instruction-tuned variants, making their results better than expected. Incorrect prompt templates or generation length can decrease benchmark performance, as well as using 4-bit quantization. Using sampling instead of greedy decoding can increase variance, especially with higher temperature values. We found that precision and 8-bit quantization have less influence on benchmark results.

  • Single-pass end-to-end neural decompilation using copying mechanism

    by Gergő Szalay, Máté Bálint Poór, Balázs Pintér, Tibor Gregorics

  • Fine-Tuning CodeLlama to Fix Bugs

    by Balázs Szalontai, András Vadász, Tamás Márton, Balázs Pintér, Tibor Gregorics


  • Idiomatizing Python Source Code Using Different Recurrent Architectures

    by Balázs Szalontai, Tamás Márton, Ákos Kukucska, Balázs Pintér, Tibor Gregorics

  • Localizing and Idiomatizing Nonidiomatic Python Code with Deep Learning

    by Balázs Szalontai, Ákos Kukucska, András Vadász, Balázs Pintér, Tibor Gregorics


  • Open Access

    Flexible Example-Based Program Synthesis on Tree-Structured Function Compositions

    by Bálint Mucsányi, Bálint Gyarmathy, Ádám Czapp, Balázs Pintér

    We introduce a flexible program synthesis system whose task is to predict function compositions that transform given inputs to their corresponding given outputs. We process input lists in a sequential manner, allowing the system to generalize to a wide range of input lengths. We separate the operator and the operand in the lambda functions of the used higher order functions to achieve significantly wider numeric parameter ranges compared to the previous works. The evaluations show that this approach is competitive with state-of-the-art systems, while it is much more flexible in terms of the input length, the parameters of the lambda functions, and the integer range of the inputs and outputs. We extend the system to handle tree-structured function compositions by introducing two additional functions (, copy) and the ability to represent unfinished function compositions during the synthesis process. The extended system achieves state-of-the-art results while synthesizing complex function compositions with multiple forks. We believe that flexibility in these aspects is an important step towards solving real-world problems with example-based program synthesis.