AssertLLM: An Automatic Assertion Generation Framework for Hardware Verification Using Multiple Large Language Models
AssertLLM is a novel framework that leverages the power of multiple large language models (LLMs) to automate the generation of SystemVerilog Assertions (SVAs) from complex hardware design specifications, improving the efficiency and effectiveness of hardware verification.
AI 統合システムの監査可能性評価: フレームワークと学習分析ケーススタディ
AI 統合システム、特に学習分析におけるAIシステムの監査可能性を確保するためには、設計段階から監査可能性を考慮したフレームワークが必要である。
Leveraging Large Language Models for Enhanced JSON Parser Fuzzing: A Novel Approach to Bug Discovery and Behavioral Analysis
This research paper proposes JFuzz, a novel approach that integrates Large Language Models (LLMs) into JSON parser fuzzing to enhance bug discovery and analyze behavioral diversities among different parser implementations.
Exploring and Enhancing the Robustness of LLM-Powered Automated Program Repair Using Metamorphic Testing
Large language models (LLMs) show promise for automated program repair (APR) but are susceptible to code style variations. This research introduces MT-LAPR, a metamorphic testing framework that identifies and exploits these vulnerabilities to improve LLM-based APR robustness.
© 2024 by Linnk AI