ACM Computing Surveys (CSUR)

Sabbatini, Federico

doi: 10.1145/3749097pmid: N/A

Issues deriving from the opaque behaviour of prediction-effective, yet non-interpretable, machine learning predictors are being studied and analysed since many decades. One of the main research branches consists of adopting anyway the unintelligible models, thanks to their predictive performance, but queueing to the learning workflow a dedicated technique aimed at post-hoc extracting human-interpretable symbolic knowledge. Following this research line, a growing number of very different knowledge-extraction procedures have been designed over the last four decades, making it difficult for end-users and researches to orient themselves towards the selection of the most suitable one. Accordingly, this survey aims at providing a guide to perform an aware selection of the knowledge-extraction techniques that most probably fit a given task.

Shorinwa, Ola; Mei, Zhiting; Lidard, Justin; Ren, Allen Z.; Majumdar, Anirudha

doi: 10.1145/3744238pmid: N/A

The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent prompt, driving significant research efforts devoted to quantifying the uncertainty of LLMs. This survey seeks to provide an extensive review of existing uncertainty quantification methods for LLMs, identifying their salient features, along with their strengths and weaknesses. We present existing methods within a relevant taxonomy, unifying ostensibly disparate methods to aid understanding of the state-of-the-art. Furthermore, we highlight applications of uncertainty quantification methods for LLMs, spanning chatbot and textual applications to embodied artificial intelligence applications in robotics. We conclude with open research challenges in the uncertainty quantification of LLMs, seeking to motivate future research.

Kumar, Pawan; Pal, Kunwar; Govil, Mahesh Chandra

doi: 10.1145/3737280pmid: N/A

Unmanned Aerial Vehicles (UAVs) have gained significant attention in recent years for their potential applications in surveillance, monitoring, search and rescue, and mapping. However, efficient and optimal path planning remains a key challenge for UAV navigation. This survey article reviews various UAV path planning algorithms, encompassing Sampling-Based techniques, Potential Field methods, Bio-Inspired algorithms, and Artificial Intelligence-based approaches. We explore key factors affecting path planning, including environmental constraints, objectives, and uncertainties. We explore vital factors affecting path planning, including environmental constraints, objectives, and uncertainties. A comparative analysis of these techniques focuses on their strengths, weaknesses, and applicability in different UAV scenarios, including heuristic, mathematical, Bio-Inspired, and machine-learning methods. Critical parameters like path length, flight time, number of UAVs and targets, environmental dynamics, obstacle management, algorithmic approaches, real-time execution, and collision avoidance are examined. This survey aims to inform researchers, practitioners, and engineers in UAV path planning, offering insights into these techniques' challenges, limitations, and future research directions. By presenting a comprehensive overview of state-of-the-art methods and trends, our survey provides a clear understanding of the diverse path-planning strategies, their merits and demerits, and highlights key research challenges and unresolved issues in the field.

Chen, Long; Huang, Yuzhi; Dong, Junyu; Xu, Qi; Kwong, Sam; Lu, Huimin; Lu, Huchuan; Li, Chongyi

doi: 10.1145/3759243pmid: N/A

Underwater optical object detection (UOD), aiming at identifying and localising objects in underwater optical images or videos, presents significant challenges due to the optical distortion, water turbidity, and changing illumination in underwater scenes. In recent years, artificial intelligence (AI) based methods, especially deep learning methods, have shown promising performance in UOD. To further facilitate future advancements, we comprehensively study AI-based UOD. In this survey, we first categorise existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarise them by considering learning strategies, experimental datasets, learning stages, employed features or techniques, and underlying frameworks. Next, we discuss the potential challenges and suggest possible solutions and new directions. We also perform both quantitative and qualitative evaluations of mainstream algorithms across multiple benchmark datasets, taking into account the diversity and biases in experimental setups. Finally, we introduce two off-the-shelf detection analysis tools, Diagnosis and TIDE, which will examine the effects of object characteristics and various types of errors on detector performance. These tools help identify the strengths and weaknesses of different detectors, providing insights for further improvement. The source code, trained models, utilised datasets, detection results, and detection analysis tools are publicly available at https://github.com/LongChenCV/UODReview and will be regularly updated.

Abubakar, Abdullahi Kutiriko; Gillam, Lee; Sastry, Nishanth

doi: 10.1145/3765516pmid: N/A

As the 2030 deadline for achieving the Sustainable Development Goals (SDGs) approaches, the Internet of Things (IoT) has become a key enabler of sustainable development. This article presents a systematic review of IoT-SDG research from 2015–2024, mapping its applications across seven macro-sectors: health, food and agriculture, energy and environment, education and employment, industry and innovation, governance and human rights, and smart cities and smart spaces. Our analysis identifies three major trends: (i) a shift from conceptual designs to real-world deployments, including grassroots innovations in developing economies tailored to local priorities; (ii) increasing reliance on enabling technologies such as cloud, edge, and machine learning, which together enhance scalability and responsiveness; and (iii) the growing use of IoT data not only for operational efficiency, but to quantify the impact of SDG interventions and identify areas for refinement. Despite this progress, barriers remain, including limited connectivity, dependence on centralised infrastructures, and challenges of interoperability, particularly in low-resource settings. These findings underscore the need for context-specific, edge-driven architectures and scalable mobile applications that can bridge digital divides. By synthesising achievements, gaps, and future opportunities, this review offers actionable insights for policymakers, technologists, and researchers seeking to harness IoT more effectively in support of an inclusive and sustainable SDG Vision 2030.

Ding, Jingtao; Zhang, Yunke; Shang, Yu; Zhang, Yuheng; Zong, Zefang; Feng, Jie; Yuan, Yuan; Su, Hongyuan; Li, Nian; Sukiennik, Nicholas; Xu, Fengli; Li, Yong

doi: 10.1145/3746449pmid: N/A

The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence. This survey offers a comprehensive review of the literature on world models. Generally, world models are regarded as tools for either understanding the present state of the world or predicting its future dynamics. This review presents a systematic categorization of world models, emphasizing two primary functions: (1) constructing internal representations to understand the mechanisms of the world, and (2) predicting future states to simulate and guide decision-making. Initially, we examine the current progress in these two categories. We then explore the application of world models in key domains, including autonomous driving, robotics, and social simulacra, with a focus on how each domain utilizes these aspects. Finally, we outline key challenges and provide insights into potential future research directions. We summarize the representative articles along with their code repositories in https://github.com/tsinghua-fib-lab/World-Model.

Cheng, Qing; Zeng, Zefan; Hu, Xingchen; Si, Yuehang; Liu, Zhong

doi: 10.1145/3756009pmid: N/A

Event Causality Identification (ECI) has become an essential task in Natural Language Processing (NLP), focused on automatically detecting causal relationships between events within texts. This comprehensive survey systematically investigates fundamental concepts and models, developing a systematic taxonomy and critically evaluating diverse models. We begin by defining core concepts, formalizing the ECI problem, and outlining standard evaluation protocols. Our classification framework divides ECI models into two primary tasks: Sentence-level Event Causality Identification (SECI) and Document-level Event Causality Identification (DECI). For SECI, we review models employing feature pattern-based matching, machine learning classifiers, deep semantic encoding, prompt-based fine-tuning, and causal knowledge pre-training, alongside data augmentation strategies. For DECI, we focus on approaches utilizing deep semantic encoding, event graph reasoning, and prompt-based fine-tuning. Special attention is given to recent advancements in multi-lingual and cross-lingual ECI, as well as zero-shot ECI leveraging Large Language Models (LLMs). We analyze the strengths, limitations, and unresolved challenges associated with each approach. Extensive quantitative evaluations are conducted on four benchmark datasets to rigorously assess the performance of various ECI models. We conclude by discussing future research directions and highlighting opportunities to advance the field further.

Wijegunarathna, Kalana Induwara; Stock, Kristin; Jones, Christopher B.

doi: 10.1145/3763231pmid: N/A

Gazetteers typically store data on place names, place types, and the associated coordinates. They play an essential role in disambiguating place names in online geographical information retrieval systems for navigation and mapping, detecting and disambiguating place names in text, and providing coordinates. Currently, there are many gazetteers in use derived from many sources, with no commonly accepted standard for encoding the data. Most gazetteers are also very limited in the extent to which they represent the multiple facets of the named places yet they have potential to assist user search for locations with specific physical, commercial, social, or cultural characteristics. With a focus on understanding digital gazetteer technologies and advancing their future effectiveness for information retrieval, we provide a review of data sources, components, software and data management technologies, data quality and volunteered data, and methods for matching sources that refer to the same real-world places. We highlight the need for future work on richer representation of named places, the temporal evolution of place identity and location, and the development of more effective methods for data integration.

Ali, Abid; Molla, Diego

doi: 10.1145/3763245pmid: N/A

The proliferation of information-sharing platforms and the ease of access to diverse resources have led to an overwhelming volume of multimodal data that is increasingly difficult to process effectively. The integration of multiple data types, including text, images, video, and audio, highlights the growing importance of Multimodal Text Summarization (MMTS). Collecting and synthesizing existing research on this topic can provide a comprehensive foundation for advancing the field. Following a Systematic Literature Review (SLR) methodology, we addressed three pivotal research questions concerning methodologies, evaluation measures, and datasets in MMTS. Through a systematic analysis of 132 papers, we examined the strategies employed to address MMTS challenges, assessed the evaluation methods used to quantify performance, and compiled a detailed list of available datasets along with their limitations. This review offers critical insights and identifies future research directions, aiming to inform and guide continued innovation in this dynamic and evolving domain.

Qi, Minfeng; Wang, Qin; Wang, Zhipeng; Schneider, Manvir; Zhu, Tianqing; Chen, Shiping; Knottenbelt, William; Hardjono, Thomas

doi: 10.1145/3763232pmid: N/A

In this article, we present the first Systematization of Knowledge (SoK) on constructing Layer Two (L2) solutions for Bitcoin. We carefully examine a representative subset of ongoing Bitcoin L2 solutions (40 out of 335 extensively investigated cases) and provide a concise yet impactful identification of six classic design patterns through two approaches (i.e., modifying transactions and creating proofs). Notably, we are the first to incorporate the inscription technology (emerged in mid-2023), along with a series of related innovations. We further establish a reference framework that serves as a baseline criterion ideally suited for evaluating the security aspects of Bitcoin L2 solutions, and which can also be extended to broader L2 applications. We apply this framework to evaluate each of the projects we investigated. We find that the inscription-based approaches introduce new functionality (i.e., programability) to Bitcoin systems, whereas existing proof-based solutions primarily address scalability challenges. Our security analysis reveals new attack vectors targeting data/state (availability, verification), assets (withdrawal, recovery), and users (disputes, censorship).