Automated Smart Contract Summarization via LLM and Semantic Augmentation
This program is tentative and subject to change.
Smart contract code summarization can significantly facilitate the maintenance of smart contracts and mitigate their vulnerabilities. Large Language Models (LLMs), such as GPT-4o and Gemini-1.5-Pro, possess the capability to generate code summarizations from code examples embedded in prompts. However, the performance of LLMs in code summarization remains suboptimal compared to fine-tuning-based models (e.g., CodeT5+, CodeBERT). Therefore, we propose SCLA, a framework leveraging LLMs and semantic augmentation to improve code summarization performance. SCLA constructs the smart contract’s Abstract Syntax Tree (AST) to extract latent semantics, thereby forming a semantically augmented prompt. For evaluation, we utilize a large-scale dataset comprising 40,000 real-world contracts. Experimental results demonstrate that SCLA, with its enhanced prompt, significantly improves the quality of code summarizations. SCLA surpasses other state-of-the-art models (e.g., CodeBERT, CodeT5, and CodeT5+), achieving 37.53% BLEU-4, 52.54% METEOR, 56.97% ROUGE-L, and 63.44% BLEURT, respectively.
This program is tentative and subject to change.
Tue 29 OctDisplayed time zone: Pacific Time (US & Canada) change
16:30 - 17:30 | Smart contract and block chain 1NIER Track / Journal-first Papers / Research Papers / Tool Demonstrations at Gardenia | ||
16:30 15mTalk | Skyeye: Detecting Imminent Attacks via Analyzing Adversarial Smart Contracts Research Papers Haijun Wang Xi’an Jiaotong University, Yurui Hu Xi'an Jiaotong University, Hao Wu Xi'an JiaoTong University, Dijun Liu Ant Group, Chenyang Peng Xi'an Jiaotong University, Yin Wu Xi'an Jiaotong University, Ming Fan Xi'an Jiaotong University, Ting Liu Xi'an Jiaotong University | ||
16:45 15mTalk | DL4SC: a novel deep learning-based vulnerability detection framework for smart contracts Journal-first Papers | ||
17:00 10mTalk | OpenTracer: A Dynamic Transaction Trace Analyzer for Smart Contract Invariant Generation and Beyond Tool Demonstrations Zhiyang Chen University of Toronto, Ye Liu Singapore Management University, Sidi Mohamed Beillahi University of Toronto, Yi Li Nanyang Technological University, Fan Long University of Toronto | ||
17:10 10mTalk | Automated Smart Contract Summarization via LLM and Semantic Augmentation NIER Track Yingjie Mao Hainan University, Xiaoqi Li Hainan University, Wenkai Li Hainan University, Xin Wang Wuhan University, Lei Xie Hainan University |