paper-with-me

홈 › Papers

CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation

2024-08-28 · Pooja Aggarwal, Oishik Chatterjee, Ting Dai, Prateeti Mohapatra, Brent Paulovicks, Brad Blancett, Arthur De Magalhaes

The advent of large language models (LLMs) has greatly facilitated code generation, but ensuring the functional correctness of generated code remains a challenge. Traditional validation methods are often time-consuming, error-prone, and impractical for large volumes of code. We introduce CodeSift, a novel framework that leverages LLMs as the first-line filter of code validation without the need for execution, reference code, or human feedback, thereby reducing the validation effort. We assess the effectiveness of our method across three diverse datasets encompassing two programming languages. Our results indicate that CodeSift outperforms state-of-the-art code evaluation methods. Internal testing conducted with subject matter experts reveals that the output generated by CodeSift is in line with human preference, reinforcing its effectiveness as a dependable automated code validation tool.

📄 PDF Abstract BibTeX arXiv:2408.15630

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Detecting Contaminated Code-Generation Prompt Batches via Influence Functions

2026-08-14 · Francesco Quinzan, Noor Munir, Yishun Lu, Stephen Roberts arxiv

Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely on predefined threat models or known vu…

Code Generation

ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement

2024-09-12 · Oishik Chatterjee, Pooja Aggarwal, Suranjana Samanta, Ting Dai 외

In the rapidly evolving landscape of site reliability engineering (SRE), the demand for efficient and effective solutions to manage and resolve issues in site and cloud applications is paramount. This paper presents an i…

Script Generation

LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation

2025-06-12 · Ngoc Phuoc An Vo, Brent Paulovicks, Vadim Sheinin

In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is synta…

Code Generation

Safer-Instruct: Aligning Language Models with Automated Preference Data

2023-11-15 · Taiwei Shi, Kai Chen, Jieyu Zhao

Reinforcement learning from human feedback (RLHF) is a vital strategy for enhancing model capability in language models. However, annotating preference data for RLHF is a resource-intensive and creativity-demanding proce…

Diversity

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation

2021-04-15 · EMNLP 2021 11 · Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski 외

QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions. Its adaptation to Data-to-Text tasks is…

Data-to-Text GenerationQuestion GenerationQuestion-GenerationText Generation