Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 511 - 540 of 8692

Full-Text Articles in Entire DC Network

Fact-Audit: An Adaptive Multi-Agent Framework For Dynamic Fact-Checking Evaluation Of Large Language Models, Hongzhan Lin, Yang Deng, Yuxuan Gu, Wenxuan Zhang, Jing Ma, See-Kiong Ng, Tat-Seng Chua Aug 2025

Fact-Audit: An Adaptive Multi-Agent Framework For Dynamic Fact-Checking Evaluation Of Large Language Models, Hongzhan Lin, Yang Deng, Yuxuan Gu, Wenxuan Zhang, Jing Ma, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs’ fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs’ factual reasoning …

Go to article

Beware Of Your Po! Measuring And Mitigating Ai Safety Risks In Role-Play Fine-Tuning Of Llms, Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu Aug 2025

Beware Of Your Po! Measuring And Mitigating Ai Safety Risks In Role-Play Fine-Tuning Of Llms, Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, …

Go to article

Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking, Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng Aug 2025

Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking, Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng

Research Collection School Of Computing and Information Systems

Automating web navigation which aims to build a web agent that follows user instructions to complete tasks like booking flights by interacting with websites, has received increasing attention due to its practical value. Although existing web agents are mostly equipped with visual perception, planning, and memory abilities, their reasoning process are still deviate from human cognition. In this work, we study the human thought pattern to empower agent with more human-like abilities in web navigation. To tackle this problem, we propose a novel multimodal web agent framework called WebExperT, which is designed to emulate the human planning process of “thinking …

Go to article

Other Orienteering Problem Variants, Pieter Vansteenwegen, Aldy Gunawan Aug 2025

Other Orienteering Problem Variants, Pieter Vansteenwegen, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In this chapter, different variants of routing problems with profits will be discussed. Based on what is available in literature, mostly variants of the orienteering problem will be discussed. A first variant considers capacity constraints, since these appear frequently in many practical applications. Next, multi-objective orienteering problems, explicitly considering different types of profits separately are discussed. Time-dependent and stochastic travel times are also relevant for most practical applications. These are considered together with time-dependent and stochastic profits. More and more routing problems are considered together with inventory management. For routing problems with profits, this leads to the inventory orienteering problem, …

Go to article

Optimizing Group Utility In Itinerary Planning: A Strategic And Crowd-Aware Approach, Junhua Liu, Aldy Gunawan, Kristin L. Wood, Kwan Hui Lim Aug 2025

Optimizing Group Utility In Itinerary Planning: A Strategic And Crowd-Aware Approach, Junhua Liu, Aldy Gunawan, Kristin L. Wood, Kwan Hui Lim

Research Collection School Of Computing and Information Systems

Itinerary recommendation is a complex sequence prediction problem with numerous practical applications. The task becomes significantly more challenging when optimizing multiple factors simultaneously, such as user queuing times, crowd levels, attraction popularity, walking durations, and operating hours. These factors, combined with the dynamic and unpredictable nature of visitor flow, introduce substantial complexities, particularly when accounting for collective user behavior. Existing solutions often adopt a single-user perspective, overlooking critical challenges arising from natural crowd dynamics. For example, the Selfish Routing problem illustrates how individual decision-making can lead to suboptimal outcomes for the group as a whole. To address these challenges, we …

Go to article

A Review: The Beauty Of Serendipity Between Integrated Circuit Security And Artificial Intelligence, Chen Dong, Decheng Qiu, Bolun Li, Yang Yang, Chenxi Lyu, Dong Cheng, Hao Zhang, Zhenyi. Chen Aug 2025

A Review: The Beauty Of Serendipity Between Integrated Circuit Security And Artificial Intelligence, Chen Dong, Decheng Qiu, Bolun Li, Yang Yang, Chenxi Lyu, Dong Cheng, Hao Zhang, Zhenyi. Chen

Research Collection School Of Computing and Information Systems

Integrated circuits are the core of a cyber-physical system, where tens of billions of components are integrated into a tiny silicon chip to conduct complex functions. To maximize utilities, the design and manufacturing life cycle of integrated circuits rely on numerous untrustworthy third parties, forming a global supply chain model. At the same time, this model produces unpredictable and catastrophic issues, threatening the security of individuals and countries. As for guaranteeing the security of ultra-highly integrated chips, detecting slight abnormalities caused by malicious behavior in the current and voltage is challenging, as is achieving computability within a reasonable time and …

Go to article

Causalabstain: Enhancing Multilingual Llms With Causal Reasoning For Trustworthy Abstention, Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma Aug 2025

Causalabstain: Enhancing Multilingual Llms With Causal Reasoning For Trustworthy Abstention, Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to abstain when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current abstention strategies for multilingual scenarios primarily rely on generating feedback in various languages using LLMs and performing self-reflection. However, these methods can be adversely impacted by inaccuracies and biases in the generated feedback. To address this, from a causal perspective, we introduce CausalAbstain, a method that helps LLMs determine whether to utilize multiple generated feedback responses and how to identify the most useful ones. Extensive experiments demonstrate that CausalAbstain effectively …

Go to article

Advancing Molecular Graph-Text Pre-Training Via Fine-Grained Alignment, Yibo Li, Yuan Fang, Mengmei Zhang, Chuan Shi Aug 2025

Advancing Molecular Graph-Text Pre-Training Via Fine-Grained Alignment, Yibo Li, Yuan Fang, Mengmei Zhang, Chuan Shi

Research Collection School Of Computing and Information Systems

Understanding molecular structure and related knowledge is crucialfor scientific research. Recent studies integrate molecular graphswith their textual descriptions to enhance molecular representationlearning. However, they focus on the whole molecular graph andneglect frequently occurring subgraphs, known as motifs, whichare essential for determining molecular properties. Without suchfine-grained knowledge, these models struggle to generalize to un-seen molecules and tasks that require motif-level insights. To bridgethis gap, we propose FineMolTex, a novel Fine-grained Moleculargraph-Text pre-training framework to jointly learn coarse-grainedmolecule-level knowledge and fine-grained motif-level knowledge.Specifically, FineMolTex consists of two pre-training tasks: a con-trastive alignment task for coarse-grained matching and a maskedmulti-modal modeling task for …

Go to article

Equivalence And Similarity Refutation For Probabilistic Programs, Krishnendu Chatterjee, Ehsan Kafshdar Goharshady, Petr Novotný, Dorde Zikelic Aug 2025

Equivalence And Similarity Refutation For Probabilistic Programs, Krishnendu Chatterjee, Ehsan Kafshdar Goharshady, Petr Novotný, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider the problems of statically refuting equivalence and similarity of output distributions defined by a pair of probabilistic programs. Equivalence and similarity are two fundamental relational properties of probabilistic programs that are essential for their correctness both in implementation and in compilation. In this work, we present a new method for static equivalence and similarity refutation. Our method refutes equivalence and similarity by computing a function over program outputs whose expected value with respect to the output distributions of two programs is different. The function is computed simultaneously with an upper expectation supermartingale and a lower expectation submartingale for …

Go to article

Graph Positional Autoencoders As Self-Supervised Learners, Yang Liu, Deyu Bo, Wenxuan Cao, Yuan Fang, Yawen Li, Chuan Shi Aug 2025

Graph Positional Autoencoders As Self-Supervised Learners, Yang Liu, Deyu Bo, Wenxuan Cao, Yuan Fang, Yawen Li, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability. Typically, GAEs take incomplete graphs as input and predict missing elements, such as masked node features or edges. Although effective, our experimental investigation reveals that traditional feature or edge masking paradigms primarily capture low-frequency signals in the graph and fail to learn expressive structural information. To address these issues, we propose Graph Positional Autoencoders (GraphPAE), which employ a dual-path architecture to reconstruct both node features and positions. Specifically, the feature path …

Go to article

L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan Aug 2025

L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring …

Go to article

Ai-Assisted Risk Assessment In Generative Ai Governance, Wu Jiaqi Young, Fiona Fui-Hoon Nah Aug 2025

Ai-Assisted Risk Assessment In Generative Ai Governance, Wu Jiaqi Young, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Effective risk assessment is paramount for responsible generative AI (GenAI) deployment. Traditional governance approaches that rely on manual reviews are inadequate given the scale and velocity of GenAI outputs. A risk-based approach incorporating real-time monitoring and governance is paramount. In this research, we examine how the efficacy of suggestive versus supportive explanations for AI’s risk assessment of GenAI outputs is moderated by user domain expertise and AI’s risk assessment in determining user acceptance. We hypothesize that cognitive involvement increases with AI’s risk assessment, with higher risks triggering more critical evaluation. By drawing on the elaboration likelihood model, we hypothesize that …

Go to article

Prompttutor: Effects Of An Llm-Based Chatbot On Learning Outcomes And Motivation In Flipped Classrooms, Yuhao Zhang, Eng Lieh Ouh, Chong Jee Adam Ho, Siaw Ling Lo, Kar Way Tan, Feng Lin Jul 2025

Prompttutor: Effects Of An Llm-Based Chatbot On Learning Outcomes And Motivation In Flipped Classrooms, Yuhao Zhang, Eng Lieh Ouh, Chong Jee Adam Ho, Siaw Ling Lo, Kar Way Tan, Feng Lin

Research Collection School Of Computing and Information Systems

This study explores the integration of a Large Language Model (LLM) based chatbot, PromptTutor, into flipped classrooms (FC) for undergraduate Computer Science (CS) education. PromptTutor is designed to provide personalized, immediate feedback to support student learning in FC by incorporating reflective learning and scaffolding strategies. The traditional FC typically lacks this immediate feedback during the pre-class learning phase, risking decreased student motivation according to existing literature. This study examines if students improve in learning outcomes and motivation after using PromptTutor. Through a controlled crossover experiment with 50 students, the study demonstrates statistically significant improvements in students' quiz performance and motivation …

Go to article

Exploring The Capabilities Of Llms For Code-Change-Related Tasks, Lishui Fan, Jiakun Liu, Zhongxin Liu, David Lo, Xin Xia, Shanping Li Jul 2025

Exploring The Capabilities Of Llms For Code-Change-Related Tasks, Lishui Fan, Jiakun Liu, Zhongxin Liu, David Lo, Xin Xia, Shanping Li

Research Collection School Of Computing and Information Systems

Developers deal with code-change-related tasks daily, e.g., reviewing code. Pre-trained code and code-change-oriented models have been adapted to help developers with such tasks. Recently, large language models (LLMs) have shown their effectiveness in code-related tasks. However, existing LLMs for code focus on general code syntax and semantics rather than the differences between two code versions. Thus, it is an open question how LLMs perform on code-change-related tasks.To answer this question, we conduct an empirical study using 1B parameters LLMs on three code-change-related tasks, i.e., code review generation, commit message generation, and just-in-time comment update, with in-context learning (ICL) and parameter-efficient …

Go to article

Wa-Fdnet: A Unified Weight Adaptation Network For Multimodal Image Fusion And Object Detection, Yanyin Guo, Ying Luo, Junwei Li, Zhiyuan Zhang Jul 2025

Wa-Fdnet: A Unified Weight Adaptation Network For Multimodal Image Fusion And Object Detection, Yanyin Guo, Ying Luo, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Multimodal image fusion and object detection are critical tasks in computer vision, particularly in scenarios requiring robust perception under low illumination conditions. Existing approaches that attempt to combine these tasks often rely on cascaded or loosely coupled designs, which can result in suboptimal performance due to gradient conflicts and task imbalance. In this paper, we propose WA-FDNet, a novel Weight Adaptation Fusion Detection Network that unifies multimodal image fusion and object detection into a single end-to-end framework. WA-FDNet adopts a shared encoder–private decoder architecture, enabling efficient feature sharing while preserving task-specific characteristics. The image fusion branch employs a spatial attention-based …

Go to article

Instruct2see: Learning To Remove Any Obstructions Across Distributions, Junhang Li, Yu Guo, Chuhua Xian, Shengfeng He Jul 2025

Instruct2see: Learning To Remove Any Obstructions Across Distributions, Junhang Li, Yu Guo, Chuhua Xian, Shengfeng He

Research Collection School Of Computing and Information Systems

Images are often obstructed by various obstacles due to capture limitations, hindering the observation of objects of interest. Most existing methods address occlusions from specific elements like fences or raindrops, but are constrained by the wide range of real-world obstructions, making comprehensive data collection impractical. To overcome these challenges, we propose Instruct2See, a novel zero-shot framework capable of handling both seen and unseen obstacles. The core idea of our approach is to unify obstruction removal by treating it as a soft-hard mask restoration problem, where any obstruction can be represented using multi-modal prompts, such as visual semantics and textual instructions, …

Go to article

Finir: The 2nd Workshop On Financial Information Retrieval In The Era Of Generative Ai, Fengbin Zhu, Yunshan Ma, Fuli Feng, Chao Wang, Huanbo Luan, Guangnan Ye, Shuo Zhang, Dhagash Mehta, Pingping Chen, Bing Xiang, Tat‑Seng Chua Jul 2025

Finir: The 2nd Workshop On Financial Information Retrieval In The Era Of Generative Ai, Fengbin Zhu, Yunshan Ma, Fuli Feng, Chao Wang, Huanbo Luan, Guangnan Ye, Shuo Zhang, Dhagash Mehta, Pingping Chen, Bing Xiang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Recent advancements in Generative AI, such as Large Language Models (LLMs), have demonstrated remarkable success across various general tasks. Extensive studies have explored leveraging generative models in finance, but significant challenges persist. This half-day workshop explores potential approaches and research directions to address these challenges by equipping generative models with advanced Information Retrieval (IR) models. Specifically, this workshop seeks to provide a platform for discussing innovative ideas that facilitate the advancement of IR technology to enrich generative models in finance from four key perspectives: (i) financial IR techniques (ii) financial IR benchmarking and evaluation (iii) financial systems and agents/assistants (iv) …

Go to article

Mitigating Regression Faults Induced By Feature Evolution In Deep Learning Systems, Hanmo Yu, Zan Wang, Xuyang Chen, Junjie Chen, Jun Sun, Shuang Liu, Zishuo Dong Jul 2025

Mitigating Regression Faults Induced By Feature Evolution In Deep Learning Systems, Hanmo Yu, Zan Wang, Xuyang Chen, Junjie Chen, Jun Sun, Shuang Liu, Zishuo Dong

Research Collection School Of Computing and Information Systems

Deep learning (DL) systems have been widely utilized across various domains. However, the evolution of DL systems can result in regression faults. In addition to the evolution of DL systems through the incorporation of new data, feature evolution, such as the addition of new features, is also common and can introduce regression faults. In this work, we first investigate the underlying factors that are correlated with regression faults in feature evolution scenarios, i.e., redundancy and contribution shift. Based on our investigation, we propose a novel mitigation approach called FeaProtect, which aims to minimize the impact of these two factors. To …

Go to article

Crow: Eliminating Backdoors From Large Language Models Via Internal Consistency Regularization, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun Jul 2025

Crow: Eliminating Backdoors From Large Language Models Via Internal Consistency Regularization, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods—designed for vision/text classification tasks—fail for text generation. We propose Internal Consistency Regularization (CROW), a defense leveraging the observation that backdoored models exhibit unstable layer-wise hidden representations when triggered, while clean models show smooth transitions. CROW enforces consistency across layers via adversarial perturbations and regularization during finetuning, neutralizing backdoors without requiring clean reference models or trigger knowledge—only a small clean dataset. Experiments across Llama-2 (7B, 13B), CodeLlama (7B, 13B), and Mistral-7B demonstrate CROW’s effectiveness: it achieves significant reductions in attack success rates across …

Go to article

Llmscan: Causal Scan For Llm Misbehavior Detection, Mengdi Zhang, Kai Kiat Goh, Peixin Zhang, Jun Sun, Lin Xin Rose, Hongyu Zhang Jul 2025

Llmscan: Causal Scan For Llm Misbehavior Detection, Mengdi Zhang, Kai Kiat Goh, Peixin Zhang, Jun Sun, Lin Xin Rose, Hongyu Zhang

Research Collection School Of Computing and Information Systems

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMSCAN, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMSCAN systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM’s ‘brain’ behaves differently when generating harmful or untruthful responses. By analyzing …

Go to article

Efficient Prompt Tuning For Hierarchical Ingredient Recognition, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo Jul 2025

Efficient Prompt Tuning For Hierarchical Ingredient Recognition, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Fine-grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While existing approaches have shown promising results, they still require extensive training costs and focus solely on fine-grained ingredient recognition. In this paper, we address these limitations by introducing an efficient prompt-tuning framework that adapts pretrained visual-language models (VLMs), such as CLIP, to the ingredient recognition task without requiring full model finetuning. Additionally, we introduce three-level ingredient hierarchies to enhance both training performance and evaluation robustness. Specifically, we propose a hierarchical ingredient recognition task, designed to evaluate model performance …

Go to article

Dual-Target Disjointed Cross-Domain Recommendation Mediated Via Latent User Preferences, Dinh Hieu Do, Hady Wirawan Lauw Jul 2025

Dual-Target Disjointed Cross-Domain Recommendation Mediated Via Latent User Preferences, Dinh Hieu Do, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Users often navigate multiple platforms online, each characterized by its own set of scarce data. Recommender systems face a significant challenge in such fragmented environments. This paper proposes a novel approach to enhance recommendation systems by leveraging connections across distinct yet conceptually similar datasets from multiple platforms. We introduce a unique scenario of dual-target overlapping-free cross-platform recommendation, presenting a bridging mechanism to mutually improve across platforms and learn latent user preferences. Our approach addresses the data sparsity prevalent in each platform and enhances recommendation quality by harnessing redundant, rich, and similar domain data. Experiments validate the effectiveness of our method, …

Go to article

Foodlmm: A Versatile Food Assistant Using Large Multi-Modal Model, Yuehao Yin, Huiyan Qi, Bin Zhu, Jingjing Chen, Yu-Gang Jiang, Chong-Wah Ngo Jul 2025

Foodlmm: A Versatile Food Assistant Using Large Multi-Modal Model, Yuehao Yin, Huiyan Qi, Bin Zhu, Jingjing Chen, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. Nevertheless, the performance of general LMMs in specific domains is still far from satisfactory. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation and multi-round conversation. To facilitate FoodLMM to deal with tasks beyond pure text output, we introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutritional values and multiple segmentation masks. We adopt a two-stage training strategy. In the first stage, we utilize multiple …

Go to article

Unveiling Knowledge Boundary Of Large Language Models For Trustworthy Information Access, Yang Deng, Moxin Li, Liang Pang, Wenxuan Zhang, Wai Lam Jul 2025

Unveiling Knowledge Boundary Of Large Language Models For Trustworthy Information Access, Yang Deng, Moxin Li, Liang Pang, Wenxuan Zhang, Wai Lam

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have emerged as powerful tools for generating content and facilitating information seeking across diverse domains. While their integration into conversational systems opens new avenues for interactive information-seeking experiences, their effectiveness is constrained by their knowledge boundaries—the limits of what they know and their ability to provide reliable, truthful, and contextually appropriate information. Understanding these boundaries is essential for maximizing the utility of LLMs for real-time information seeking while ensuring their reliability and trustworthiness. In this tutorial, we will explore the taxonomy of knowledge boundary in LLMs, addressing their handling of uncertainty, response calibration, and mitigation of …

Go to article

Hps: Hard Preference Sampling For Human Preference Alignment, Xiandong Zou, Wanyu Lin, Yuchen Li, Pan Zhou Jul 2025

Hps: Hard Preference Sampling For Human Preference Alignment, Xiandong Zou, Wanyu Lin, Yuchen Li, Pan Zhou

Research Collection School Of Computing and Information Systems

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on PlackettLuce (PL) and Bradley-Terry (BT) models have shown promise, they face challenges such as poor handling of harmful content, inefficient use of dispreferred responses, and, specifically for PL, high computational costs. To address these issues, we propose Hard Preference Sampling (HPS), a novel framework for robust and efficient human preference alignment. HPS introduces a training loss that prioritizes the most preferred response while rejecting all dispreferred and harmful ones. It emphasizes “hard” dispreferred responses — those …

Go to article

Repairing Adversarial Texts Through Perturbation, Guoliang Dong, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay, Xinyu Wang, Ting Dai, Jie Shi, Jin Song Dong Jul 2025

Repairing Adversarial Texts Through Perturbation, Guoliang Dong, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay, Xinyu Wang, Ting Dai, Jie Shi, Jin Song Dong

Research Collection School Of Computing and Information Systems

It is known that neural networks are subject to attacks through adversarial perturbations. Worse yet, such attacks are impossible to eliminate, i.e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training. Multiple approaches have been developed to detect and reject such adversarial inputs. Rejecting suspicious inputs however may not be always feasible or ideal. First, normal inputs may be rejected due to false alarms generated by the detection algorithm. Second, denial-of-service attacks may be conducted by feeding such systems with adversarial inputs. To address this, in this work, we focus on the text domain and …

Go to article

Understanding The Bad Development Practices Of Android Custom Permissions In The Wild, Xiaohan Zhang, Zhiyuan Yu, Xinghua Li, Cen Zhang, Cong Sun, Ning Zhang, Robert H. Deng Jul 2025

Understanding The Bad Development Practices Of Android Custom Permissions In The Wild, Xiaohan Zhang, Zhiyuan Yu, Xinghua Li, Cen Zhang, Cong Sun, Ning Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Android system provides application developers with the ability to define custom permissions, which serve to moderate the sharing of resources and interactions with other applications. However, poor development practices of developers can render the permission mechanism ineffective, weakening the system protection. This paper presents a comprehensive examination of the problematic practices surrounding custom permissions employed by developers, referred to as Bad Practices of Custom Permissions (BPCP issues). To accomplish this, we conducted an empirical study and identified nine common BPCP issue patterns that can lead to various adverse consequences, such as installation failures, crashes, or even component hijacking. To automatically …

Go to article

Runtime Anomaly Detection For Drones: An Integrated Rule-Mining And Unsupervised Learning Approach, Ivan Wei Han Tan, Wei Minn, Christopher M. Poskitt, Lwin Khin Shar, Lingxiao Jiang Jul 2025

Runtime Anomaly Detection For Drones: An Integrated Rule-Mining And Unsupervised Learning Approach, Ivan Wei Han Tan, Wei Minn, Christopher M. Poskitt, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, have witnessed a remarkable surge in popularity due to their versatile applications. These cyber-physical systems depend on multiple sensor inputs, such as cameras, GPS receivers, accelerometers, and gyroscopes, with faults potentially leading to physical instability and serious safety concerns. To mitigate such risks, anomaly detection has emerged as a crucial safeguarding mechanism, capable of identifying the physical manifestations of emerging issues and allowing operators to take preemptive action at runtime. Recent anomaly detection methods based on LSTM neural networks have shown promising results, but three challenges persist: the need for models …

Go to article

Diversity Optimization For Travelling Salesman Problem Via Deep Reinforcement Learning, Qi Li, Zhiguang Cao, Yining Ma, Yaoxin Wu, Yue-Jiao Gong Jul 2025

Diversity Optimization For Travelling Salesman Problem Via Deep Reinforcement Learning, Qi Li, Zhiguang Cao, Yining Ma, Yaoxin Wu, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution TSP (MSTSP), we propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy. Concretely, on the one hand, a Relativization Filter (RF) is designed to enhance the robustness of the encoder to affine transformations of the instances, so as to potentially improve the quality of the found solutions. On the other hand, a Multi-Attentive Adaptive Active Search (MA3S) is tailored to allow the decoders to strike a …

Go to article

An Efficient Diffusion-Based Non-Autoregressive Solver For Traveling Salesman Problem, Mingzhao Wang, You Zhou, Zhiguang Cao, Yubin Xiao, Xuan Wu, Wei Pang, Yuan Jiang, Hui Yang, Peng Zhao, Yuanshu Li Jul 2025

An Efficient Diffusion-Based Non-Autoregressive Solver For Traveling Salesman Problem, Mingzhao Wang, You Zhou, Zhiguang Cao, Yubin Xiao, Xuan Wu, Wei Pang, Yuan Jiang, Hui Yang, Peng Zhao, Yuanshu Li

Research Collection School Of Computing and Information Systems

Recent advances in neural models have shown considerable promise in solving Traveling Salesman Problems (TSPs) without relying on much hand-crafted engineering. However, while non-autoregressive (NAR) approaches benefit from faster inference through parallelism, they typically deliver solutions of inferior quality compared to autoregressive ones. To enhance the solution quality while maintaining fast inference, we propose DEITSP, a diffusion model with efficient iterations tailored for TSP that operates in a NAR manner. Firstly, we introduce a one-step diffusion model that integrates the controlled discrete noise addition process with self-consistency enhancement, enabling optimal solution prediction through simultaneous denoising of multiple solutions. Secondly, we …

Go to article

First Prev Next Last