93 citations · 385 across the 72 of their papers we have counts for
43 papers · 1 filter
AI Safety: Not Optional, Not Later
Qinghua Lu, Yoshua Bengio
Incidents show that AI safety failures often arise across multiple layers. We present a safety-by-design assurance architecture combining model-level supervision, such as Scientist…
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…
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…
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…
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…
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…
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…
PTMPicker: Facilitating Efficient Pretrained Model Selection for Application Developers
Pei Liu, Terry Zhuo, Jiawei Deng +4
The rapid emergence of pretrained models (PTMs) has attracted significant attention from both Deep Learning (DL) researchers and downstream application developers. However, selecti…
RAGOps: Operating and Managing Retrieval-Augmented Generation Pipelines
Xiwei Xu, Hans Weytjens, Dawen Zhang +3
Recent studies show that 60% of LLM-based compound systems in enterprise environments leverage some form of retrieval-augmented generation (RAG), which enhances the relevance and a…
SeeAction: Towards Reverse Engineering How-What-Where of HCI Actions from Screencasts for UI Automation
Dehai Zhao, Zhenchang Xing, Qinghua Lu +2
UI automation is a useful technique for UI testing, bug reproduction, and robotic process automation. Recording user actions with an application assists rapid development of UI aut…
An Extended Pattern Collection for Blockchain-based Applications
Xiwei Xu, Cesare Pautasso, Sin Kuang Lo +3
Blockchain is an emerging technology that enables new forms of decentralized software architectures, where distributed components can reach agreements on shared system states witho…
Architectural Patterns for Designing Quantum Artificial Intelligence Systems
Mykhailo Klymenko, Thong Hoang, Xiwei Xu +4
Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversa…
DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
Mingyue Yuan, Jieshan Chen, Zhenchang Xing +6
The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's V0, yet surfaced challenges in design quality (e.g., accessibility,…
Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead
Yanqi Su, Zhenchang Xing, Chong Wang +4
Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from the end-user's perspective. Although ET…
From Exploration to Revelation: Detecting Dark Patterns in Mobile Apps
Jieshan Chen, Zhen Wang, Jiamou Sun +5
Mobile apps are essential in daily life but frequently employ deceptive patterns, such as visual emphasis or linguistic nudging, to manipulate user behavior. Existing research larg…
Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture
Boming Xia, Qinghua Lu, Liming Zhu +3
Large Language Models (LLMs) have enabled the emergence of LLM agents, systems capable of pursuing under-specified goals and adapting after deployment. Evaluating such agents is ch…
"I Don't Use AI for Everything": Exploring Utility, Attitude, and Responsibility of AI-empowered Tools in Software Development
Shidong Pan, Litian Wang, Tianyi Zhang +4
AI-empowered tools have emerged as a transformative force, fundamentally reshaping the software development industry and promising far-reaching impacts across diverse sectors. This…
A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model
Jingwen Zhou, Qinghua Lu, Jieshan Chen +4
The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detailed architecture design poses signific…
Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents
Md Shamsujjoha, Qinghua Lu, Dehai Zhao +1
Foundation Model (FM)-based agents are revolutionizing application development across various domains. However, their rapidly growing capabilities and autonomy have raised signific…
Refactoring to Pythonic Idioms: A Hybrid Knowledge-Driven Approach Leveraging Large Language Models
Zejun Zhang, Zhenchang Xing, Xiaoxue Ren +2
Pythonic idioms are highly valued and widely used in the Python programming community. However, many Python users find it challenging to use Pythonic idioms. Adopting a rule-based…
An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping
Boming Xia, Qinghua Lu, Liming Zhu +1
The advent of advanced AI underscores the urgent need for comprehensive safety evaluations, necessitating collaboration across communities (i.e., AI, software engineering, and gove…
Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective
Dawen Zhang, Boming Xia, Yue Liu +6
The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data pat…
Towards a Responsible AI Metrics Catalogue: A Collection of Metrics for AI Accountability
Boming Xia, Qinghua Lu, Liming Zhu +3
Artificial Intelligence (AI), particularly through the advent of large-scale generative AI (GenAI) models such as Large Language Models (LLMs), has become a transformative element…
Let's Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain
Qing Huang, Zhenyu Wan, Zhenchang Xing +4
API recommendation methods have evolved from literal and semantic keyword matching to query expansion and query clarification. The latest query clarification method is knowledge gr…