activity
20222026
most citedBlockchain-Empowered Trustworthy Data Sharing: Fundamentals, Applications, and Challenges

63 citations · 246 across the 57 of their papers we have counts for

collaborators
Showing cs.SEShow all

33 papers · 1 filter

cs.SE2026

Uncertainty Propagation in LLM-Based Systems

Boming Xia, Liming Zhu, Erdun Gao +3

Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are compound systems in which uncertai…

cs.SE2026★ 1 cited

Still Manual? Automated Linter Configuration via DSL-Based LLM Compilation of Coding Standards

Zejun Zhang, Yixin Gan, Zhenchang Xing +5

Coding standards are essential for maintaining consistent and high-quality code across teams and projects. Linters help developers enforce these standards by detecting code violati…

cs.SE2026

A Structured Approach to Safety Case Construction for AI Systems

Sung Une Lee, Liming Zhu, Md Shamsujjoha +4

Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or n…

cs.SE2025

MARIA: A Framework for Marginal Risk Assessment without Ground Truth in AI Systems

Jieshan Chen, Suyu Ma, Qinghua Lu +2

Before deploying an AI system to replace an existing process, it must be compared with the incumbent to ensure improvement without added risk. Traditional evaluation relies on grou…

cs.SE2025★ 3 cited

AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents

Qinghua Lu, Dehai Zhao, Yue Liu +6

The emergence of foundation models (FMs) has enabled the development of highly capable and autonomous agents, unlocking new application opportunities across a wide range of domains…

cs.SE2025

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows

Jingwen Zhou, Jieshan Chen, Qinghua Lu +2

Large Language Model (LLM) agentic systems are software systems powered by LLMs that autonomously reason, plan, and execute multi-step workflows to achieve human goals, rather than…