Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Emerging Science Journal
Yuriy Perezhohin
1) NOVA Information Management School (NOVA IMS), Universidade NOVA de Lisboa, 1070-312 Lisboa, Portugal. 2) Remynd, Alameda Bonifacio Lazaro Lozano, nº 15, 1º C, 2780-125 Oeiras
Environmental Science

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Enhancing Small Language Models for Code Generation via Strategic Decomposition and Filtering Yuriy Perezhohin; Fabian Collao; Mauro Castelli
Emerging Science Journal Vol. 10 No. 2 (2026): April
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-02-011

Abstract

This study addresses the challenge of enhancing Small Language Models (SLMs) for complex code generation tasks requiring structured planning, which current models struggle with due to their monolithic, single-pass generation approach. A three-stage pipeline architecture is proposed that decouples strategic planning from implementation: (1) an SLM generates diverse natural language strategies at high temperature, (2) a filtering mechanism selects high-quality strategies while removing noise, and (3) refined strategies guide a specialized coding model for final implementation. The approach was evaluated on the ClassEval benchmark for class-level code generation. The pipeline enabled a 1.5B parameter model to achieve 13% class success rate, representing a 30% relative improvement over direct generation (10%) and competitive performance with models 5-8 times larger. Critically, effective strategy filtering proved more important than strategy diversity, with simple pattern-based filters successfully mitigating SLM artifacts like few-shot contamination. This work demonstrates that structured, inference-time computation offers an efficient alternative to parameter scaling, with strategic noise reduction being the key driver of performance gains in resource-constrained models.
Co-Authors Fabian Collao Mauro Castelli