Newest papers

Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation

Brhane Team, Tiantian Yang, Nikta Akbarpour, Simone Bartucci, Francesco Calimeri, Song Wang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25616 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Grandes modelos de comportamento semicorretais (LLMs) demonstram fortes capacidades de geração de código, mas muitas vezes lutam com a correção funcional devido a requisitos comportamentais implícitos ou ambíguos. Nós apresentamos o CG2, um quadro de geração de código orientado por contrato que traduz tarefas de linguagem natural em contratos comportamentais estruturados que especificam interfaces, pré-condições, pós-condições e invariantes. O CG2 fina-tune um LLM para gerar esses contratos e introduz um processo de validação e reparação semântica iterativa para identificar e corrigir tarefas incompletas, inconsistentes ou incorretas antes de orientar um modelo de geração de código subsequente inalterado. Nós avaliamos o CG2 em 1,007

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) demonstrate strong code-generation capabilities but often struggle with functional correctness due to implicit or ambiguous behavioral requirements. We present CG2, a contract-guided code generation framework that translates natural-language tasks into structured behavioral contracts specifying interfaces, preconditions, postconditions, and invariants. CG2 fine-tunes an LLM to generate these contracts and introduces an iterative semantic validation and repair process to identify and correct incomplete, inconsistent, or incorrect specifications before guiding an unchanged downstream code-generation model. We evaluate CG2 on 1,007 held-out tasks using five code LLMs: DeepSeek-Coder-V2-Lite-Instruct, Ministral-3-14B-Instruct-2512, Qwen2.5-Coder-14B-Instruct, Qwen2.5-Coder-32B-Instruct, and Qwen3.5-27B. Results show that CG2 consistently improves pass@1 over direct code generation by 1.49-3.27 percentage points (7.58%-22.45% relative improvement) and over contract guidance without fine-tuning by 1.19-2.38 percentage points (7.04%-14.65% relative improvement). Manual analysis further reveals that semantically correct contracts are associated with higher code-generation accuracy. These findings demonstrate that explicitly specifying and validating behavioral requirements can improve functional correctness without modifying downstream code-generation models.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Correctness, Computer science, Process (computing), Code (set theory), Perspective (graphical), Programming language

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange