arXiv subjects

Liming Zhu

Publications and source records attributed to Liming Zhu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Responsible AI Question Bank: A Comprehensive Tool for AI Risk Assessment

The rapid growth of Artificial Intelligence (AI) has underscored the urgent need for responsible AI practices. Despite increasing interest, a comprehensive AI risk assessment toolkit remains lacking. This study introduces our Responsible AI (RAI) Question Bank, a comprehensive framework and tool designed to support diverse AI initiatives. By integrating AI ethics principles such as fairness, transparency, and accountability into a structured question format, the RAI Question Bank aids in identifying potential risks, aligning with emerging regulations like the EU AI Act, and enhancing overall AI governance. A key benefit of the RAI Question Bank is its systematic approach to linking lower-level risk questions to higher-level ones and related themes, preventing siloed assessments and ensuring a cohesive evaluation process. Case studies illustrate the practical application of the RAI Question Bank in assessing AI projects, from evaluating risk factors to informing decision-making processes. The study also demonstrates how the RAI Question Bank can be used to ensure compliance with standards, mitigate risks, and promote the development of trustworthy AI systems. This work advances RAI by providing organizations with a valuable tool to navigate the complexities of ethical AI development and deployment while ensuring comprehensive risk management.

cs.CY↗

arXiv2025

Towards Advancing Code Generation with Large Language Models: A Research Roadmap

Recently, we have witnessed the rapid development of large language models, which have demonstrated excellent capabilities in the downstream task of code generation. However, despite their potential, LLM-based code generation still faces numerous technical and evaluation challenges, particularly when embedded in real-world development. In this paper, we present our vision for current research directions, and provide an in-depth analysis of existing studies on this task. We propose a six-layer vision framework that categorizes code generation process into distinct phases, namely Input Phase, Orchestration Phase, Development Phase, and Validation Phase. Additionally, we outline our vision workflow, which reflects on the currently prevalent frameworks. We systematically analyse the challenges faced by large language models, including those LLM-based agent frameworks, in code generation tasks. With these, we offer various perspectives and actionable recommendations in this area. Our aim is to provide guidelines for improving the reliability, robustness and usability of LLM-based code generation systems. Ultimately, this work seeks to address persistent challenges and to provide practical suggestions for a more pragmatic LLM-based solution for future code generation endeavors.

cs.SE↗

arXiv2024

Architectural Patterns for Designing Quantum Artificial Intelligence Systems

Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without compromising accuracy. However, moving beyond proof-of-concept or simulations to develop practical applications of these systems while ensuring high software quality faces significant challenges due to the limitations of quantum hardware and the underdeveloped knowledge base in software engineering for such systems. In this work, we have conducted a systematic mapping study to identify the challenges and solutions associated with the software architecture of quantum-enhanced artificial intelligence systems. The results of the systematic mapping study reveal several architectural patterns that describe how quantum components can be integrated into inference engines, as well as middleware patterns that facilitate communication between classical and quantum components. Each pattern realises a trade-off between various software quality attributes, such as efficiency, scalability, trainability, simplicity, portability, and deployability. The outcomes of this work have been compiled into a catalogue of architectural patterns.

cs.SE↗

arXiv2024

DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models

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, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics.

cs.SE↗

arXiv2024

Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead

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 has proven effective in system-level testing of interactive systems, the need for manual execution has hindered large-scale adoption. In this work, we explore the feasibility, challenges and road ahead of automated scenario-based ET (a.k.a soap opera testing). We conduct a formative study, identifying key insights for effective manual soap opera testing and challenges in automating the process. We then develop a multi-agent system leveraging LLMs and a Scenario Knowledge Graph (SKG) to automate soap opera testing. The system consists of three multi-modal agents, Planner, Player, and Detector that collaborate to execute tests and identify potential bugs. Experimental results demonstrate the potential of automated soap opera testing, but there remains a significant gap compared to manual execution, especially under-explored scenario boundaries and incorrectly identified bugs. Based on the observation, we envision road ahead for the future of automated soap opera testing, focusing on three key aspects: the synergy of neural and symbolic approaches, human-AI co-learning, and the integration of soap opera testing with broader software engineering practices. These insights aim to guide and inspire the future research.

cs.SE↗

arXiv2024

Survey Insights on M365 Copilot Adoption

Australia's National Science Agency conducted a six-month trial of M365 Copilot starting in January 2024 as part of an Australian Government initiative. Three hundred licenses were distributed across CSIRO using a persona-based approach to ensure diversity of roles and attributes among participants. As a scientific research organisation with a unique operational context, our objective was to study the use of M365 Copilot on enhancing productivity, efficiency, and creativity as well as overall satisfaction and ethical considerations. This paper presents the results from two surveys, conducted before and after the trial. The results showed mixed outcomes, with participants reporting improved productivity and efficiency in structured tasks such as meeting summaries and email drafting. Gaps were identified in advanced functionalities and integration, which limited Copilot's overall effectiveness. Satisfaction levels were generally positive, but user experiences varied in certain areas. Ethical concerns, particularly around data privacy, became more pronounced post-trial. These findings highlight Copilot's potential and the need for further refinement to meet users' diverse needs.

cs.HC↗

arXiv2024

AgentOps: Enabling Observability of LLM Agents

Large language model (LLM) agents have demonstrated remarkable capabilities across various domains, gaining extensive attention from academia and industry. However, these agents raise significant concerns on AI safety due to their autonomous and non-deterministic behavior, as well as continuous evolving nature . From a DevOps perspective, enabling observability in agents is necessary to ensuring AI safety, as stakeholders can gain insights into the agents' inner workings, allowing them to proactively understand the agents, detect anomalies, and prevent potential failures. Therefore, in this paper, we present a comprehensive taxonomy of AgentOps, identifying the artifacts and associated data that should be traced throughout the entire lifecycle of agents to achieve effective observability. The taxonomy is developed based on a systematic mapping study of existing AgentOps tools. Our taxonomy serves as a reference template for developers to design and implement AgentOps infrastructure that supports monitoring, logging, and analytics. thereby ensuring AI safety.

cs.AI↗

arXiv2024

Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective

The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data patterns. However, these advancements come with heightened concerns over data privacy and copyright infringement, primarily due to the reliance on vast datasets for model training. Traditional approaches like differential privacy, machine unlearning, and data poisoning only offer fragmented solutions to these complex issues. Our paper delves into the multifaceted challenges of privacy and copyright protection within the data lifecycle. We advocate for integrated approaches that combines technical innovation with ethical foresight, holistically addressing these concerns by investigating and devising solutions that are informed by the lifecycle perspective. This work aims to catalyze a broader discussion and inspire concerted efforts towards data privacy and copyright integrity in Generative AI.

cs.SE↗

arXiv2024

Provably Unlearnable Data Examples

The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels such that the data samples are converted into Unlearnable Examples (UEs). Nevertheless, the absence of mechanisms to verify the robustness of UEs against uncertainty in unauthorized models and their training procedures engenders several under-explored challenges. First, it is hard to quantify the unlearnability of UEs against unauthorized adversaries from different runs of training, leaving the soundness of the defense in obscurity. Particularly, as a prevailing evaluation metric, empirical test accuracy faces generalization errors and may not plausibly represent the quality of UEs. This also leaves room for attackers, as there is no rigid guarantee of the maximal test accuracy achievable by attackers. Furthermore, we find that a simple recovery attack can restore the clean-task performance of the classifiers trained on UEs by slightly perturbing the learned weights. To mitigate the aforementioned problems, in this paper, we propose a mechanism for certifying the so-called $(q, η)$-Learnability of an unlearnable dataset via parametric smoothing. A lower certified $(q, η)$-Learnability indicates a more robust and effective protection over the dataset. Concretely, we 1) improve the tightness of certified $(q, η)$-Learnability and 2) design Provably Unlearnable Examples (PUEs) which have reduced $(q, η)$-Learnability.

cs.LG↗

arXiv2024

Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents

Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents, which can leverage distinguished reasoning and language processing capabilities to takes a proactive, autonomous role to pursue users' goals. Nevertheless, there is a lack of systematic knowledge to guide practitioners in designing the agents considering challenges of goal-seeking (including generating instrumental goals and plans), such as hallucinations inherent in foundation models, explainability of reasoning process, complex accountability, etc. To address this issue, we have performed a systematic literature review to understand the state-of-the-art foundation model-based agents and the broader ecosystem. In this paper, we present a pattern catalogue consisting of 18 architectural patterns with analyses of the context, forces, and trade-offs as the outcomes from the previous literature review. We propose a decision model for selecting the patterns. The proposed catalogue can provide holistic guidance for the effective use of patterns, and support the architecture design of foundation model-based agents by facilitating goal-seeking and plan generation.

cs.AI↗

arXiv2024

LuaTaint: A Static Analysis System for Web Configuration Interface Vulnerability of Internet of Things Devices

The diversity of web configuration interfaces for IoT devices has exacerbated issues such as inadequate permission controls and insecure interfaces, resulting in various vulnerabilities. Owing to the varying interface configurations across various devices, the existing methods are inadequate for identifying these vulnerabilities precisely and comprehensively. This study addresses these issues by introducing an automated vulnerability detection system, called LuaTaint. It is designed for the commonly used web configuration interface of IoT devices. LuaTaint combines static taint analysis with a large language model (LLM) to achieve widespread and high-precision detection. The extensive traversal of the static analysis ensures the comprehensiveness of the detection. The system also incorporates rules related to page handler control logic within the taint detection process to enhance its precision and extensibility. Moreover, we leverage the prodigious abilities of LLM for code analysis tasks. By utilizing LLM in the process of pruning false alarms, the precision of LuaTaint is enhanced while significantly reducing its dependence on manual analysis. We develop a prototype of LuaTaint and evaluate it using 2,447 IoT firmware samples from 11 renowned vendors. LuaTaint has discovered 111 vulnerabilities. Moreover, LuaTaint exhibits a vulnerability detection precision rate of up to 89.29%.

cs.CR↗

arXiv2024

Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning

Recent studies indicate that large multimodal models (LMMs) potentially act as general-purpose assistants and are highly robust against different distributions. Despite this, domain-specific adaptation is still necessary particularly in specialized areas like healthcare. Due to the impracticality of fine-tuning LMMs given their vast parameter space, this work investigates in-context learning (ICL) as an effective alternative for enhancing LMMs' adaptability. Our study addresses this by evaluating an unsupervised ICL method which selects in-context examples through a nearest example search based on feature similarity. We uncover that its effectiveness is limited by the deficiencies of pre-trained vision encoders under distribution shift scenarios. To address these challenges, we propose InvariantSelectPR, a novel method leveraging Class-conditioned Contrastive Invariance (CCI) for more robust demonstration selection. Specifically, CCI enhances pre-trained vision encoders by improving their discriminative capabilities across different classes and ensuring invariance to domain-specific variations. This enhancement allows the encoders to effectively identify and retrieve the most informative examples, which are then used to guide LMMs in adapting to new query samples under varying distributions. Our experiments show that InvariantSelectPR substantially improves the adaptability of LMMs, achieving significant performance gains on benchmark datasets, with a 34.2%$\uparrow$ accuracy increase in 7-shot on Camelyon17 and 16.9%$\uparrow$ increase in 7-shot on HAM10000 compared to the baseline zero-shot performance.

cs.CV↗

arXiv2024

Achieving Responsible AI through ESG: Insights and Recommendations from Industry Engagement

As Artificial Intelligence (AI) becomes integral to business operations, integrating Responsible AI (RAI) within Environmental, Social, and Governance (ESG) frameworks is essential for ethical and sustainable AI deployment. This study examines how leading companies align RAI with their ESG goals. Through interviews with 28 industry leaders, we identified a strong link between RAI and ESG practices. However, a significant gap exists between internal RAI policies and public disclosures, highlighting the need for greater board-level expertise, robust governance, and employee engagement. We provide key recommendations to strengthen RAI strategies, focusing on transparency, cross-functional collaboration, and seamless integration into existing ESG frameworks.

cs.CY↗

arXiv2024

Integrating ESG and AI: A Comprehensive Responsible AI Assessment Framework

Artificial Intelligence (AI) is a widely developed and adopted technology across entire industry sectors. Integrating environmental, social, and governance (ESG) considerations with AI investments is crucial for ensuring ethical and sustainable technological advancement. Particularly from an investor perspective, this integration not only mitigates risks but also enhances long-term value creation by aligning AI initiatives with broader societal goals. Yet, this area has been less explored in both academia and industry. To bridge the gap, we introduce a novel ESG-AI framework, which is developed based on insights from engagements with 28 companies and comprises three key components. The framework provides a structured approach to this integration, developed in collaboration with industry practitioners. The ESG-AI framework provides an overview of the environmental and social impacts of AI applications, helping users such as investors assess the materiality of AI use. Moreover, it enables investors to evaluate a company's commitment to responsible AI through structured engagements and thorough assessment of specific risk areas. We have publicly released the framework and toolkit in April 2024, which has received significant attention and positive feedback from the investment community. This paper details each component of the framework, demonstrating its applicability in real-world contexts and its potential to guide ethical AI investments.

cs.AI↗

arXiv2024

Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text generation from LLMs. However, how the outputs from RAG-based LLMs are affected by slightly different inputs is not well studied. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We systematically evaluate the effect of such prefixes on RAG by introducing a novel optimization technique called Gradient Guided Prompt Perturbation (GGPP). GGPP achieves a high success rate in steering outputs of RAG-based LLMs to targeted wrong answers. It can also cope with instructions in the prompts requesting to ignore irrelevant context. We also exploit LLMs' neuron activation difference between prompts with and without GGPP perturbations to give a method that improves the robustness of RAG-based LLMs through a highly effective detector trained on neuron activation triggered by GGPP generated prompts. Our evaluation on open-sourced LLMs demonstrates the effectiveness of our methods.

cs.CL↗

arXiv2024

A Reference Architecture for Designing Foundation Model based Systems

The release of ChatGPT, Gemini, and other large language model has drawn huge interests on foundations models. There is a broad consensus that foundations models will be the fundamental building blocks for future AI systems. However, there is a lack of systematic guidance on the architecture design. Particularly, the the rapidly growing capabilities of foundations models can eventually absorb other components of AI systems, posing challenges of moving boundary and interface evolution in architecture design. Furthermore, incorporating foundations models into AI systems raises significant concerns about responsible and safe AI due to their opaque nature and rapidly advancing intelligence. To address these challenges, the paper first presents an architecture evolution of AI systems in the era of foundation models, transitioning from "foundation-model-as-a-connector" to "foundation-model-as-a-monolithic architecture". The paper then identifies key design decisions and proposes a pattern-oriented reference architecture for designing responsible foundation-model-based systems. The patterns can enable the potential of foundation models while ensuring associated risks.

cs.CL↗

arXiv2024

Learning Interpretable Scheduling Algorithms for Data Processing Clusters

Workloads in data processing clusters are often represented in the form of DAG (Directed Acyclic Graph) jobs. Scheduling DAG jobs is challenging. Simple heuristic scheduling algorithms are often adopted in practice in production data centres. There is much room for scheduling performance optimisation for cost saving. Recently, reinforcement learning approaches (like decima) have been attempted to optimise DAG job scheduling and demonstrate clear performance gain in comparison to traditional algorithms. However, reinforcement learning (RL) approaches face their own problems in real-world deployment. In particular, their black-box decision making processes and generalizability in unseen workloads may add a non-trivial burden to the cluster administrators. Moreover, adapting RL models on unseen workloads often requires significant amount of training data, which leaves edge cases run in a sub-optimal mode. To fill the gap, we propose a new method to distill a simple scheduling policy based on observations of the behaviours of a complex deep learning model. The simple model not only provides interpretability of scheduling decisions, but also adaptive to edge cases easily through tuning. We show that our method achieves high fidelity to the decisions made by deep learning models and outperforms these models when additional heuristics are taken into account.

cs.DC↗

arXiv2024

An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping

The advent of advanced AI underscores the urgent need for comprehensive safety evaluations, necessitating collaboration across communities (i.e., AI, software engineering, and governance). However, divergent practices and terminologies across these communities, combined with the complexity of AI systems-of which models are only a part-and environmental affordances (e.g., access to tools), obstruct effective communication and comprehensive evaluation. This paper proposes a framework for AI system evaluation comprising three components: 1) harmonised terminology to facilitate communication across communities involved in AI safety evaluation; 2) a taxonomy identifying essential elements for AI system evaluation; 3) a mapping between AI lifecycle, stakeholders, and requisite evaluations for accountable AI supply chain. This framework catalyses a deeper discourse on AI system evaluation beyond model-centric approaches.

cs.SE↗