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

Korean

대규모 특정 언어 행동 모델 (LLM)은 강력한 코드 생성 기능을 보여주지만 종종 암시적 또는 불확실한 행동 요구 사항으로 인해 기능적 정확성에 어려움을 겪습니다. 우리는 CG2를 제시합니다. CG2는 암시적 인 코드 생성 프레임 워크를 구조화 된 행동 특정 계약으로 번역합니다. 우리는 변하지 않은 내부 코드 생성 모델을 지시하기 전에 불완전한, 불일치 또는 잘못된 행동 작업을 식별하고 수정하기 위해 계약 지시된 코드 생성 프레임 워크 프레임 워크를 소개합니다. CG2는 5 개의 코드 LLM을 사용하여 1,007 개의 실행 작업에 CG2를 평가합니다: DeepSeek-Coder-V2-Lite-

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