Digital Commons Network^™

Assessing The Robustness Of Test Selection Methods For Deep Neural Networks, Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Wei Ma, Mike Papadakis, Lei Ma, Yves Le Traon

Research Collection School Of Computing and Information Systems

Regularly testing deep learning-powered systems on newly collected data is critical to ensure their reliability, robustness, and efficacy in real-world applications. This process is demanding due to the significant time and human effort required for labeling new data. While test selection methods alleviate manual labor by labeling and evaluating only a subset of data while meeting testing criteria, we observe that such methods with reported promising results are simply evaluated, e.g., testing on original test data. The question arises: are they always reliable? In this article, we explore when and to what extent test selection methods fail. First, we identify …

How To Enable Effective Cooperation Between Humans And Nlp Models: A Survey Of Principles, Formalizations, And Beyond, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua, Jimmy Huang

Research Collection School Of Computing and Information Systems

With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans. This evolution has birthed a novel paradigm in NLP, i.e., human-model cooperation, that has yielded remarkable progress in numerous NLP tasks in recent years. In this paper, we take the first step to present a thorough review of human-model cooperation, exploring its principles, formalizations, and open challenges. In particular, we introduce a new taxonomy that provides a unified perspective to summarize existing approaches. Also, we discuss potential frontier areas and their corresponding …

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 …

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, …

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, …

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 …

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 …

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 …

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 …

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 …

Improved Secure Two-Party Computation From A Geometric Perspective, Hao Guo, Liqiang Peng, Haiyang Xue, Li Peng, Weiran Liu, Zhe Liu, Lei. Hu

Research Collection School Of Computing and Information Systems

Multiplication and other non-linear operations are widely recognized as the most costly components of secure two-party computation (2PC) based on linear secret sharing. Moreover, the comparison protocol (or Wrap protocol) is essential for various operations such as truncation, signed extension, and signed non-uniform multiplication. This paper aims to optimize these protocols by avoiding invoking the costly comparison protocol, thereby improving their efficiency.We propose a novel approach to study 2PC from a geometric perspective. Specifically, we interpret the two shares of a secret as the horizontal and vertical coordinates of a point in a Cartesian coordinate system, with the secret itself …

Let’S Teach More Accurate And Inclusive History! The Case Of Islamic Contributions To Mathematics And Science, Nuh Aydin

Journal of Humanistic Mathematics

Schools commonly teach a history of mathematics and science that is Eurocentric. This selective version of the history of science, called Classical Narrative by some, is rooted in colonial times and mindset, and has reinforced certain negative opinions about other cultures. It ignores or downplays contributions to mathematics and sciences from non-western civilizations, and falsely attributes many scientific discoveries to European scholars. Medieval Islamic Civilization, which had strong connections to Renaissance Europe, serves as a clear example of how this narrative is distorted. Based on research on primary sources since the middle of the 20th century, we now know that …

From Shudu [Sudoku 數獨] To Dushu [Learning Of Mathematics 讀數]?, Man Keung Siu

Journal of Humanistic Mathematics

The puzzle game Sudoku has been popular for over two decades, and even at one time became a craze for the public. This paper will briefly describe what the game is, a little bit of its history, and how to play it, but will leave the details to the many published books about the game. Some interesting and difficult mathematical problems relevant to the game will be highlighted, again leaving the detailed discussion to specific books published on this issue. The main point the paper tries to focus on is a discussion on the cognitive and the psychological aspects of …

Small Number And The Old Game, Veselin Jungic

Journal of Humanistic Mathematics

Through a conversation between Small Number and his Auntie, this article describes the Throwing Game, a Haida tradition recorded by John Swanton in 1905. Several mathematical concepts that may be associated to the game are mentioned.

A Dualistic Interpretation Of Mathematical Creation Through Art And Argumentation, Sofia Almpani, Petros Stefaneas, Mihir Chakraborty

Journal of Humanistic Mathematics

Creativity, informal reasoning and dynamic exchange of ideas form the pulsating heart of mathematical creation. In this approach, the concept of a mathematical object surpasses conventional boundaries of formal presentation, as they also encompass the intention to prove, significant creative stages within the proving, and the overall experience of prover's journey, which may involve arguments, debates, discovery insights, aesthetic visualizations, and narrative elements. In this paper we present two conceptual frameworks, namely Argumentation-based Proof-Events Calculus (APEC) and Mathematical RUPAs, in order to provide distinct yet interconnected perspectives on informal thinking, knowledge creation, and proving in mathematics. Following the two perspectives, …

Revisiting A 19th Century Vector Algebra Book, Olcay Coskun, Alp Eden, Ersin Karabudak

Journal of Humanistic Mathematics

Hidden gems of mathematics can be recovered when one digs into what might seem an obscure text. In 1882, military officer Vidinli Hüseyin Tevfik Pasha published a book on vector algebra titled Linear Algebra. In this article we revisit the second edition of this book, emphasizing the special multiplication that we call the ’v-product’. This product has both geometric and algebraic characteristics. We attempt to clarify its relationship with complex and quaternion multiplication both geometrically and algebraically. The resulting algebra is called the Vidinli algebra. This algebra admits a Lie algebra structure that gives rise to Heisenberg algebra. We introduce …

Memes As An Effective Approach To Increase Public Engagement With Mathematical Concepts, Juan M. Romero, Carlos Trenado

Journal of Humanistic Mathematics

A meme is a graphical concept or cultural item that is disseminated via the Internet, often through social media platforms. Memes serve as a mechanism for replicating cultural traits by incorporating aspects of cultural mutation and evolution. The potential of memes in learning and education has been emphasized in several recent studies. The present article examines the impact of memes in increasing public engagement with mathematics and mathematical concepts. By focusing on memes that exhibit specific attributes—such as emotional facial expressions of recognizable human characters and dialogues emphasizing the usefulness or beauty of a mathematical concept—we observe a significant increase …

Evaluating Methods Used To Quantify Racial Segregation, Sarah Cannon, Zarina Dhillon

Journal of Humanistic Mathematics

Racial segregation has long been a problem in communities across the United States. One approach to help understand such an important issue is to attempt to describe it quantitatively. Many metrics have been developed, all with various strengths and weaknesses, but none fully capture the nuances of this complicated issue. This work provides an overview of four of the mathematical approaches that have been developed to study segregation, explains how they function using small examples, and compares and contrasts their effectiveness in various situations. We then focus on segregation in Los Angeles (LA) County, including a detailed exploration of the …

Graphical Timetables As A Real-Life Example Of Different Representations Of Functions, Olav G. Imenes

Journal of Humanistic Mathematics

This paper examines 203 pre-service teachers' reactions and learning when they were introduced to a real-life situation in which it is natural to publish officially both graphs and tables of a given function: the situation of operating a railway. I found that almost all the pre-service teachers managed the easiest tasks, like calculating speeds, distances, and time for train represented by graphs. However, the more complicated tasks, which required interpretations of the graphs and tables, such as planning for a delayed train, finding which trains were locals, freight trains etc., were more difficult for them to grasp. There were few …

Front Matter

Journal of Humanistic Mathematics

No abstract provided.

Long Distance Love, Isaiah Hinton

Night Flight: Online Literary Journal

The story portrays the journey of a girl named Michelle, who faced numerous challenges and obstacles in her life. She always felt like an outcast and unwanted by her family, which made her feel depressed and upset. However, she managed to find happiness by not expecting anything from others and being a go-getter. She worked hard to achieve her goals, maintained straight A's in high school, and had two jobs. Michelle's life took a turn for the better on October 29th, when she received the love and affection she had craved her entire life. The story is a reminder that …

Between Shadows And Dreams, Alonso Medina

Night Flight: Online Literary Journal

This story follows Valentina Torres, a 15-year-old girl living in Puerto Vallarta, Mexico, who grapples with self-worth and the pressures of being underestimated. Val has always felt small in a world that seems to favor the louder, more visible individuals. Raised by hard-working parents, Val learns the value of determination and education. Despite the challenges of balancing school, work, and family responsibilities, Val maintains a deep sense of justice that often gets her into conflict with others, especially with Mia Perez, a popular but cruel classmate. After enduring a series of insults from Mia, Val finally confronts her in a …

The Tax Adviser, Volume 12, Number 11, November 1981, American Institute Of Certified Public Accountants

Tax Adviser

No abstract provided.

Tax Trends, E. S. Linett

Tax Adviser

No abstract provided.

Washington Report: Tax Division Comments On Sec. 385 Regs., Kenneth F. Thomas, Peter F. Zimmermann, American Institute Of Certified Public Accountants. Federal Tax Division

Tax Adviser

No abstract provided.

Sale Of A Residence: A Closer Look, Patrick B. Dorr, John H. Wilguess

Tax Adviser

No abstract provided.

Tax Clinic, Darwin Broenen

Tax Adviser

No abstract provided.

Hershey Foods Corp.: Diabetic Shock For The Irs, Wesley Yang, Leroy L. Metz

Tax Adviser

No abstract provided.

Highlights Of The Economic Recovery Tax Act Of 1981, Gerald W. Padwe, David D. Green

Tax Adviser

No abstract provided.

Critique Of Pure Reason, Immanuel Kant

Hannah Arendt Marginalia - All

Macmillan: St Martin’s Press, 1963

Call #: B2778 .E5 S5

Contains marginalia.

PDF Information: 247 pages – 112.5mb