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

Physical Sciences and Mathematics Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 151 - 180 of 6956

Full-Text Articles in Physical Sciences and Mathematics

Learning To Search Feasible And Infeasible Regions Of Routing Problems With Flexible Neural K-Opt, Yining Ma, Zhiguang Cao, Yew Meng Chee Dec 2023

Learning To Search Feasible And Infeasible Regions Of Routing Problems With Flexible Neural K-Opt, Yining Ma, Zhiguang Cao, Yew Meng Chee

Research Collection School Of Computing and Information Systems

In this paper, we present Neural k-Opt (NeuOpt), a novel learning-to-search (L2S) solver for routing problems. It learns to perform flexible k-opt exchanges based on a tailored action factorization method and a customized recurrent dual-stream decoder. As a pioneering work to circumvent the pure feasibility masking scheme and enable the autonomous exploration of both feasible and infeasible regions, we then propose the Guided Infeasible Region Exploration (GIRE) scheme, which supplements the NeuOpt policy network with feasibility-related features and leverages reward shaping to steer reinforcement learning more effectively. Besides, we further equip NeuOpt with dynamic data augmentations during inference for more …

Go to article

Neural Multi-Objective Combinatorial Optimization With Diversity Enhancement, Jinbiao Chen, Zizhen Zhang, Zhiguang Cao, Yaoxin Wu, Yining Ma, Te Ye, Jiahai Wang Dec 2023

Neural Multi-Objective Combinatorial Optimization With Diversity Enhancement, Jinbiao Chen, Zizhen Zhang, Zhiguang Cao, Yaoxin Wu, Yining Ma, Te Ye, Jiahai Wang

Research Collection School Of Computing and Information Systems

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more …

Go to article

Wsdms: Debunk Fake News Via Weakly Supervised Detection Of Misinforming Sentences With Contextualized Social Wisdom, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Zhiwei Yang Dec 2023

Wsdms: Debunk Fake News Via Weakly Supervised Detection Of Misinforming Sentences With Contextualized Social Wisdom, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Zhiwei Yang

Research Collection School Of Computing and Information Systems

In recent years, we witness the explosion of false and unconfirmed information (i.e., rumors) that went viral on social media and shocked the public. Rumors can trigger versatile, mostly controversial stance expressions among social media users. Rumor verification and stance detection are different yet relevant tasks. Fake news debunking primarily focuses on determining the truthfulness of news articles, which oversimplifies the issue as fake news often combines elements of both truth and falsehood. Thus, it becomes crucial to identify specific instances of misinformation within the articles. In this research, we investigate a novel task in the field of fake news …

Go to article

Truncated Affinity Maximization: One-Class Homophily Modeling For Graph Anomaly Detection, Hezhe Qiao, Guansong Pang Dec 2023

Truncated Affinity Maximization: One-Class Homophily Modeling For Graph Anomaly Detection, Hezhe Qiao, Guansong Pang

Research Collection School Of Computing and Information Systems

We reveal a one-class homophily phenomenon, which is one prevalent property we find empirically in real-world graph anomaly detection (GAD) datasets, i.e., normal nodes tend to have strong connection/affinity with each other, while the homophily in abnormal nodes is significantly weaker than normal nodes. However, this anomaly-discriminative property is ignored by existing GAD methods that are typically built using a conventional anomaly detection objective, such as data reconstruction. In this work, we explore this property to introduce a novel unsupervised anomaly scoring measure for GAD – local node affinity – that assigns a larger anomaly score to nodes that are …

Go to article

Disentangling Transformer Language Models As Superposed Topic Models, Jia Peng Lim, Hady Wirawan Lauw Dec 2023

Disentangling Transformer Language Models As Superposed Topic Models, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Topic Modelling is an established research area where the quality of a given topic is measured using coherence metrics. Often, we infer topics from Neural Topic Models (NTM) by interpreting their decoder weights, consisting of top-activated words projected from individual neurons. Transformer-based Language Models (TLM) similarly consist of decoder weights. However, due to its hypothesised superposition properties, the final logits originating from the residual path are considered uninterpretable. Therefore, we posit that we can interpret TLM as superposed NTM by proposing a novel weight-based, model-agnostic and corpus-agnostic approach to search and disentangle decoder-only TLM, potentially mapping individual neurons to multiple …

Go to article

Make The U In Uda Matter: Invariant Consistency Learning For Unsupervised Domain Adaptation, Zhongqi Yue, Qianru Sun, Hanwang Zhang Dec 2023

Make The U In Uda Matter: Invariant Consistency Learning For Unsupervised Domain Adaptation, Zhongqi Yue, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Domain Adaptation (DA) is always challenged by the spurious correlation between domain-invariant features (e.g., class identity) and domain-specific features (e.g., environment) that do not generalize to the target domain. Unfortunately, even enriched with additional unsupervised target domains, existing Unsupervised DA (UDA) methods still suffer from it. This is because the source domain supervision only considers the target domain samples as auxiliary data (e.g., by pseudo-labeling), yet the inherent distribution in the target domain—where the valuable de-correlation clues hide—is disregarded. We propose to make the U in UDA matter by giving equal status to the two domains. Specifically, we learn an …

Go to article

Exploring Students' Adoption Of Chatgpt As A Mentor For Undergraduate Computing Projects: Pls-Sem Analysis, Gottipati Swapna, Kyong Jin Shim, Shankararaman, Venky Dec 2023

Exploring Students' Adoption Of Chatgpt As A Mentor For Undergraduate Computing Projects: Pls-Sem Analysis, Gottipati Swapna, Kyong Jin Shim, Shankararaman, Venky

Research Collection School Of Computing and Information Systems

As computing projects increasingly become a core component of undergraduate courses, effective mentorship is crucial for supporting students' learning and development. Our study examines the adoption of ChatGPT as a mentor for undergraduate computing projects. It explores the impact of ChatGPT mentorship, specifically, skills development, and mentor responsiveness, i.e., ChatGPT's responsiveness to students' needs and requests. We utilize PLS-SEM to investigate the interrelationships between different factors and develop a model that captures their contribution to the effectiveness of ChatGPT as a mentor. The findings suggest that mentor responsiveness and technical/design support are key factors for the adoption of AI tools …

Go to article

Transformer-Based Multi-Task Learning For Crisis Actionability Extraction, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint Dec 2023

Transformer-Based Multi-Task Learning For Crisis Actionability Extraction, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint

Research Collection School Of Computing and Information Systems

Social media has become a valuable information source for crisis informatics. While various methods were proposed to extract relevant information during a crisis, their adoption by field practitioners remains low. In recent fieldwork, actionable information was identified as the primary information need for crisis responders and a key component in bridging the significant gap in existing crisis management tools. In this paper, we proposed a Crisis Actionability Extraction System for filtering, classification, phrase extraction, severity estimation, localization, and aggregation of actionable information altogether. We examined the effectiveness of transformer-based LSTM-CRF architecture in Twitter-related sequence tagging tasks and simultaneously extracted actionable …

Go to article

Distxplore: Distribution-Guided Testing For Evaluating And Enhancing Deep Learning Systems, Longtian Wang, Xiaofei Xie, Xiaoning Du, Meng Tian, Qing Guo, Zheng Yang, Chao Shen Dec 2023

Distxplore: Distribution-Guided Testing For Evaluating And Enhancing Deep Learning Systems, Longtian Wang, Xiaofei Xie, Xiaoning Du, Meng Tian, Qing Guo, Zheng Yang, Chao Shen

Research Collection School Of Computing and Information Systems

Deep learning (DL) models are trained on sampled data, where the distribution of training data differs from that of real-world data (i.e., the distribution shift), which reduces the model's robustness. Various testing techniques have been proposed, including distribution-unaware and distribution-aware methods. However, distribution-unaware testing lacks effectiveness by not explicitly considering the distribution of test cases and may generate redundant errors (within same distribution). Distribution-aware testing techniques primarily focus on generating test cases that follow the training distribution, missing out-of-distribution data that may also be valid and should be considered in the testing process. In this paper, we propose a novel …

Go to article

Designing Large-Scale Intelligent Collaborative Platform For Freight Forwarders, Pang Jin Tan, Shih-Fen Cheng, Richard Chen Dec 2023

Designing Large-Scale Intelligent Collaborative Platform For Freight Forwarders, Pang Jin Tan, Shih-Fen Cheng, Richard Chen

Research Collection School Of Computing and Information Systems

In this paper, we propose to design a large-scale intelligent collaborative platform for freight forwarders. This platform is based on a mathematical programming formulation and an efficient solution approach. Forwarders are middlemen who procure container capacities from carriers and sell them to shippers to serve their transport requests. However, due to demand uncertainty, they often either over-procure or under-procure capacities. We address this with our proposed platform where forwarders can collaborate and share capacities, allowing one's transport requests to be potentially shipped on another forwarder's container. The result is lower total costs for all participating forwarders. The collaboration can be …

Go to article

Software Architecture In Practice: Challenges And Opportunities, Zhiyuan Wan, Yun Zhang, Xin Xia, Yi Jiang, David Lo Dec 2023

Software Architecture In Practice: Challenges And Opportunities, Zhiyuan Wan, Yun Zhang, Xin Xia, Yi Jiang, David Lo

Research Collection School Of Computing and Information Systems

Software architecture has been an active research field for nearly four decades, in which previous studies make significant progress such as creating methods and techniques and building tools to support software architecture practice. Despite past efforts, we have little understanding of how practitioners perform software architecture related activities, and what challenges they face. Through interviews with 32 practitioners from 21 organizations across three continents, we identified challenges that practitioners face in software architecture practice during software development and maintenance. We reported on common software architecture activities at software requirements, design, construction and testing, and maintenance stages, as well as corresponding …

Go to article

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie Dec 2023

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie

Research Collection School Of Computing and Information Systems

The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning …

Go to article

A Reliable And Secure Mobile Cyber-Physical Digital Microfluidic Biochip For Intelligent Healthcare, Yinan Yao, Decheng Qiu, Huangda Liu, Zhongliao Yang, Ximeng Liu, Yang Yang, Chen Dong Dec 2023

A Reliable And Secure Mobile Cyber-Physical Digital Microfluidic Biochip For Intelligent Healthcare, Yinan Yao, Decheng Qiu, Huangda Liu, Zhongliao Yang, Ximeng Liu, Yang Yang, Chen Dong

Research Collection School Of Computing and Information Systems

Digital microfluidic, as an emerging and potential technology, diversifies the biochemical applications platform, such as protein dilution sewage detection. At present, a vast majority of universal cyberphysical digital microfluidic biochips (DMFBs) transmit data through wires via personal computers and microcontrollers (like Arduino), consequently, susceptible to various security threats and with the popularity of wireless devices, losing competitiveness gradually. On the premise that security be ensured first and foremost, calls for wireless portable, safe, and economical DMFBs are imperative to expand their application fields, engage more users, and cater to the trend of future wireless communication. To this end, a new …

Go to article

How Helpful Do Novice Programmers Find The Feedback Of An Automated Repair Tool?, Oka Kurniawan, Christopher M. Poskitt, Ismam Al Hoque, Norman Tiong Seng Lee, Cyrille Jégourel, Nachamma Sockalingam Dec 2023

How Helpful Do Novice Programmers Find The Feedback Of An Automated Repair Tool?, Oka Kurniawan, Christopher M. Poskitt, Ismam Al Hoque, Norman Tiong Seng Lee, Cyrille Jégourel, Nachamma Sockalingam

Research Collection School Of Computing and Information Systems

Immediate feedback has been shown to improve student learning. In programming courses, immediate, automated feedback is typically provided in the form of pre-defined test cases run by a submission platform. While these are excellent for highlighting the presence of logical errors, they do not provide novice programmers enough scaffolding to help them identify where an error is or how to fix it. To address this, several tools have been developed that provide richer feedback in the form of program repairs. Studies of such tools, however, tend to focus more on whether correct repairs can be generated, rather than how novices …

Go to article

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2023

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

This paper explores ChatGPT’s potential in aiding government agencies, drawing from a case study based on a government agency in Singapore. While ChatGPT’s text generation abilities offer promise, it brings inherent challenges, including data opacity, potential misinformation, and occasional errors. These issues are especially critical in government decision-making.Public administration’s core values of transparency and accountability magnify these concerns. Ensuring AI alignment with these principles is imperative, given the potential repercussions on policy outcomes and citizen trust.AI explainability plays a central role in ChatGPT’s adoption within government agencies. To address these concerns, we propose strategies like prompt engineering, data governance, and …

Go to article

Extending The Horizon By Empowering Government Customer Service Officers With Acqar For Enhanced Citizen Service Delivery, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2023

Extending The Horizon By Empowering Government Customer Service Officers With Acqar For Enhanced Citizen Service Delivery, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

A previous study on the use of the Empath library in the prediction of Service Level Agreements (SLA) reveals the quality levels required for meaningful interaction between government customer service officers and citizens. On the other hand, past implementation of the Citizen Question-Answer system (CQAS), a type of Question-Answer model, suggests that such models if put in place can empower government customer service officers to reply faster and better with recommended answers. This study builds upon the research outcomes from both arenas of studies and introduces an innovative system design that allows the officers to incorporate the outputs from Empath …

Go to article

Class Participation: Using Technology To Enhance Efficiency And Fairness, Benjamin Gan, Eng Lieh Ouh Dec 2023

Class Participation: Using Technology To Enhance Efficiency And Fairness, Benjamin Gan, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

Class participation can be considered as contribution to discussion, attendance, presentations, unsolicited responses, questions, comments, etc. What counts may vary across individual teachers. The more students participate, the less memorization they do, and the more they engage in higher levels of thinking, including interpretation, analysis, and synthesis. However, only a handful of students in many classrooms participate regularly, a phenomenon dubbed as "consolidation of responsibility". This study provides a literature review of inclass participation, as well as pedagogies and technologies that enhance participation. Pedagogies such as active learning, group learning, project-based learning and flipped classroom. Technologies to automate attendance taking, …

Go to article

Sustainability Projects With A Community Partner: A Social Norm Nudging Effort, Benjamin Gan, Thomas Menkhoff, Eng Lieh Ouh Dec 2023

Sustainability Projects With A Community Partner: A Social Norm Nudging Effort, Benjamin Gan, Thomas Menkhoff, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

Singapore students from two inter-disciplinary courses worked with stakeholders of a local business association community partner on a series of sustainability topics to learn about climate change, its effects, and actions to mitigate them. They empathized with the association stakeholders, proposed a digital technology solution, tested their prototypes, and presented the final action plans. After the projects were completed, we found climate proficient (83%), motivated (83%), engaged (97%), and satisfied (70%) students; and two influencing predictors: interest/enjoyment and emotional engagement. The study results suggest that getting students interested and emotionally engaged in sustainability projects is an important first step towards …

Go to article

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee Dec 2023

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee

Research Collection School Of Computing and Information Systems

Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633 memes annotated with their entities and relations, and propose a novel MERF pipeline that extracts entities and their relationships in memes. Our framework combines state-of-the-art techniques from natural language processing and computer vision to extract text and image features and infer relationships between entities in memes. We evaluate the proposed framework on a …

Go to article

Neural Airport Ground Handling, Yaoxin Wu, Jianan Zhou, Yunwen Xia, Xianli Zhang, Zhiguang Cao, Jie Zhang Dec 2023

Neural Airport Ground Handling, Yaoxin Wu, Jianan Zhou, Yunwen Xia, Xianli Zhang, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation. Such a problem involves the interplay among the operations that leads to NP-hard problems with complex constraints. Hence, existing methods for AGH are usually designed with massive domain knowledge but still fail to yield high-quality solutions efficiently. In this paper, we aim to enhance the solution quality and computation efficiency for solving AGH. Particularly, we first model AGH as a multiple-fleet vehicle routing problem (VRP) with miscellaneous constraints including precedence, time windows, …

Go to article

Exgen: Ready-To-Use Exercise Generation In Introductory Programming Courses, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna Dec 2023

Exgen: Ready-To-Use Exercise Generation In Introductory Programming Courses, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna

Research Collection School Of Computing and Information Systems

In introductory programming courses, students as novice programmers would benefit from doing frequent practices set at a difficulty level and concept suitable for their skills and knowledge. However, setting many good programming exercises for individual learners is very time-consuming for instructors. In this work, we propose an automated exercise generation system, named ExGen, which leverages recent advances in pre-trained large language models (LLMs) to automatically create customized and ready-to-use programming exercises for individual students ondemand. The system integrates seamlessly with Visual Studio Code, a popular development environment for computing students and software engineers. ExGen effectively does the following: 1) maintaining …

Go to article

A Black-Box Attack On Code Models Via Representation Nearest Neighbor Search, Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu Dec 2023

A Black-Box Attack On Code Models Via Representation Nearest Neighbor Search, Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu

Research Collection School Of Computing and Information Systems

Existing methods for generating adversarial code examples face several challenges: limted availability of substitute variables, high verification costs for these substitutes, and the creation of adversarial samples with noticeable perturbations. To address these concerns, our proposed approach, RNNS, uses a search seed based on historical attacks to find potential adversarial substitutes. Rather than directly using the discrete substitutes, they are mapped to a continuous vector space using a pre-trained variable name encoder. Based on the vector representation, RNNS predicts and selects better substitutes for attacks. We evaluated the performance of RNNS across six coding tasks encompassing three programming languages: Java, …

Go to article

Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring Via Constructing The Optimal Subgraph Of Demonstrations And Prompts, Jiashu Pu, Ling Cheng, Lu Fan, Tangjie Lv, Rongsheng Zhang Dec 2023

Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring Via Constructing The Optimal Subgraph Of Demonstrations And Prompts, Jiashu Pu, Ling Cheng, Lu Fan, Tangjie Lv, Rongsheng Zhang

Research Collection School Of Computing and Information Systems

The use of modern Large Language Models (LLMs) as chatbots still has some problems such as hallucinations and lack of empathy. Identifying these issues can help improve chatbot performance. The community has been continually iterating on reference-free dialogue evaluation methods based on large language models (LLMs) that can be readily applied. However, many of these LLM-based metrics require selecting specific datasets and developing specialized training tasks for different evaluation dimensions (e.g., coherence, informative). The developing step can be time-consuming and may need to be repeated for new evaluation dimensions. To enable efficient and flexible adaptation to diverse needs of dialogue …

Go to article

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2023

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

This paper explores ChatGPT’s potential in aiding government agencies, drawing from a case study based on a government agency in Singapore. While ChatGPT’s text generation abilities offer promise, it brings inherent challenges, including data opacity, potential misinformation, and occasional errors. These issues are especially critical in government decision-making.Public administration’s core values of transparency and accountability magnify these concerns. Ensuring AI alignment with these principles is imperative, given the potential repercussions on policy outcomes and citizen trust.AI explainability plays a central role in ChatGPT’s adoption within government agencies. To address these concerns, we propose strategies like prompt engineering, data governance, and …

Go to article

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu Dec 2023

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

Causality-based recommendation systems focus on the causal effects of user-item interactions resulting from item exposure (i.e., which items are recommended or exposed to the user), as opposed to conventional correlation-based recommendation. They are gaining popularity due to their multi-sided benefits to users, sellers and platforms alike. However, existing causality-based recommendation methods require additional input in the form of exposure data and/or propensity scores (i.e., the probability of exposure) for training. Such data, crucial for modeling causality in recommendation, are often not available in real-world situations due to technical or privacy constraints. In this paper, we bridge the gap by proposing …

Go to article

Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang Dec 2023

Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang

Research Collection School Of Computing and Information Systems

Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the fish is not inside the fishbowl. The case, however, may be different for a vision-language model, whose reasoning could gravitate towards the common scenario that the fish is inside the bowl, despite the visual input. In this paper, we introduce a novel probing dataset named ROME (reasoning beyond commonsense knowledge) to evaluate whether the state-of-the-art pre-trained vision-language models have the reasoning capability to correctly interpret …

Go to article

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun Dec 2023

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have made remarkable strides in various tasks. However, whether they are competitive few-shot solvers for information extraction (IE) tasks and surpass fine-tuned small Pre-trained Language Models (SLMs) remains an open problem. This paper aims to provide a thorough answer to this problem, and moreover, to explore an approach towards effective and economical IE systems that combine the strengths of LLMs and SLMs. Through extensive experiments on nine datasets across four IE tasks, we show that LLMs are not effective few-shot information extractors in general, given their unsatisfactory performance in most settings and the high latency and …

Go to article

Robust Prompt Optimization For Large Language Models Against Distribution Shifts, Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua Dec 2023

Robust Prompt Optimization For Large Language Models Against Distribution Shifts, Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt optimization using labeled task data. We reveal that these prompt optimization techniques are vulnerable to distribution shifts such as subpopulation shifts, which are common for LLMs in real-world scenarios such as customer reviews analysis. In this light, we propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled …

Go to article

Covariance-Based Causal Debiasing For Entity And Relation Extraction, Lin Ren, Yongbin Liu, Yixin Cao, Chunping Ouyang Dec 2023

Covariance-Based Causal Debiasing For Entity And Relation Extraction, Lin Ren, Yongbin Liu, Yixin Cao, Chunping Ouyang

Research Collection School Of Computing and Information Systems

Joint entity and relation extraction tasks aim to recognize named entities and extract relations simultaneously. Suffering from a variety of data biases, such as data selection bias, and distribution bias (out of distribution, long-tail distribution), serious concerns can be witnessed to threaten the model’s transferability, robustness, and generalization. In this work, we address the above problems from a causality perspective. We propose a novel causal framework called covariance and variance optimization framework (OVO) to optimize feature representations and conduct general debiasing. In particular, the proposed covariance optimizing (COP) minimizes characterizing features’ covariance for alleviating the selection and distribution bias and …

Go to article

Deepaco: Neural-Enhanced Ant Systems For Combinatorial Optimization, Haoran Ye, Jiarui Wang, Zhiguang Cao, Helan Liang, Yong Li Dec 2023

Deepaco: Neural-Enhanced Ant Systems For Combinatorial Optimization, Haoran Ye, Jiarui Wang, Zhiguang Cao, Helan Liang, Yong Li

Research Collection School Of Computing and Information Systems

Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally, customizing ACO for a specific problem requires the expert design of knowledge-driven heuristics. In this paper, we propose DeepACO, a generic framework leveraging deep reinforcement learning to automate heuristic designs. DeepACO serves to strengthen the heuristic measures of existing ACO algorithms and dispense with laborious manual design in future ACO applications. As a neural-enhanced meta-heuristic, DeepACO consistently outperforms its ACO counterparts on eight COPs using a single neural model and a single set of hyperparameters. As a Neural Combinatorial Optimization …

Go to article

First Prev Next Last