paper-with-me

홈 › Papers

Clover: Closed-Loop Verifiable Code Generation

2023-10-26 · Chuyue Sun, Ying Sheng, Oded Padon, Clark Barrett

The use of large language models for code generation is a rapidly growing trend in software development. However, without effective methods for ensuring the correctness of generated code, this trend could lead to undesirable outcomes. In this paper, we introduce a new approach for addressing this challenge: the Clover paradigm, short for Closed-Loop Verifiable Code Generation, which uses consistency checking to provide a strong filter for incorrect code. Clover performs consistency checks among code, docstrings, and formal annotations. The checker is implemented using a novel integration of formal verification tools and large language models. We provide a theoretical analysis to support our thesis that Clover should be effective at consistency checking. We also empirically investigate its performance on a hand-designed dataset (CloverBench) featuring annotated Dafny programs at a textbook level of difficulty. Experimental results show that for this dataset: (i) LLMs are reasonably successful at automatically generating formal specifications; and (ii) our consistency checker achieves a promising acceptance rate (up to 87%) for correct instances while maintaining zero tolerance for adversarial incorrect ones (no false positives). Clover also discovered 6 incorrect programs in the existing human-written dataset MBPP-DFY-50.

📄 PDF Abstract BibTeX arXiv:2310.17807

Code (2)

ChuyueSun/Clover 공식 구현
jmbuba/llm-semantic-perf

Tasks

Code Generationmbpp

Similar Papers 제목 키워드 기반

CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning

2026-05-14 · Sining Ang, Yuguang Yang, Canyu Chen, Yan Wang arxiv

End-to-end autonomous driving planners are commonly trained by imitating a single logged trajectory, yet evaluated by rule-based planning metrics that measure safety, feasibility, progress, and comfort. This creates a tr…

Autonomous Driving

Cost-effective Instruction Learning for Pathology Vision and Language Analysis

2024-07-25 · Kaitao Chen, Mianxin Liu, Fang Yan, Lei Ma 외

The advent of vision-language models fosters the interactive conversations between AI-enabled models and humans. Yet applying these models into clinics must deal with daunting challenges around large-scale training data,…

Few-Shot LearningLanguage ModellingLarge Language Model

Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding

2024-08-01

Large Language Models (LLMs) frequently suffer from inefficiencies, largely attributable to the discord between the requirements of auto-regressive decoding and the architecture of contemporary GPUs. Recently, regressive…

GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation

2026-05-26 · Boxiang Qiu, Liliang Chen, Yue Liao, Nan Wang 외 arxiv

We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation framework of Genie Envisioner, GE-Sim 2.0 …

Video Generation

From Failure to Mastery: Generating Hard Samples for Tool-use Agents

2026-01-04 · Bingguang Hao, Zengzhuang Xu, Yuntao Wen, Xinyi Xu 외 arxiv

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, o…