ACM Computing Surveys最新文献

{"title":"Lost in Translation? Found in Evaluation: A Comprehensive Survey on Sentence-Level Translation Evaluation","authors":"Ananya Mukherjee, Manish Shrivastava","doi":"10.1145/3735970","DOIUrl":"https://doi.org/10.1145/3735970","url":null,"abstract":"Machine Translation (MT) revolutionizes cross-lingual communication but is prone to errors, necessitating thorough evaluation for enhancement. Translation quality can be assessed by humans and automatic evaluation metrics. Human evaluation, though valuable, is costly and subject to limitations in scalability and consistency. While automated metrics supplement manual evaluations, this field still has considerable potential for development. However, there exists prior survey work on automatic evaluation metrics, it is worth noting that most of these are focused on resource-rich languages, leaving a significant gap in evaluating MT outputs across other language families. To bridge this gap, we present an exhaustive survey, encompassing discussions on MT meta-evaluation datasets, human assessments, and diverse metrics. We categorize both human and automatic evaluation approaches, and offer decision trees to aid in selecting the appropriate approach. Additionally, we evaluate sentences across languages, domains and linguistic features, and further meta-evaluate the metrics by correlating them with human scores. We critically examine the limitations and challenges inherent in current datasets and evaluation approaches. We propose suggestions for future research aimed at enhancing MT evaluation, including the importance of diverse and well-distributed datasets, the refinement of human evaluation methodologies, and the development of robust metrics that closely align with human judgments.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"18 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Instrumental Variables in Causal Inference and Machine Learning: A Survey","authors":"Anpeng Wu, Kun Kuang, Ruoxuan Xiong, Fei Wu","doi":"10.1145/3735969","DOIUrl":"https://doi.org/10.1145/3735969","url":null,"abstract":"Causal inference is the process of drawing conclusions about causal relationships between variables using a combination of assumptions, study designs, and estimation strategies. In machine learning, causal inference is crucial for uncovering the mechanisms behind complex systems and making informed decisions. This paper provides a comprehensive overview of using Instrumental Variables (IVs) in causal inference and machine learning, with a focus on addressing unobserved confounding that affects both treatment and outcome variables. We review identification conditions under standard assumptions in the IV literature. In this paper, we explore three key research areas of IV methods: Two-Stage Least Squares (2SLS) regression, control function (CFN) approaches, and recent advances in IV learning methods. These methods cover both classical causal inference approaches and recent advancements in machine learning research. Additionally, we provide a summary of available datasets and algorithms for implementing these methods. Furthermore, we introduce a variety of applications of IV methods in real-world scenarios. Lastly, we identify open problems and suggest future research directions to further advance the field. A toolkit of reviewed IV methods with machine learning (MLIV) is available at https://github.com/causal-machine-learning-lab/mliv.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"1 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fundamental Capabilities and Applications of Large Language Models: A Survey","authors":"Jiawei Li, Yang Gao, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, Yiguan Lin, Bin Xu, Bowen Ren, Chong Feng, Heyan Huang","doi":"10.1145/3735632","DOIUrl":"https://doi.org/10.1145/3735632","url":null,"abstract":"Large Language Models (LLMs) have demonstrated remarkable effectiveness across various domain-specific applications. However, which fundamental capabilities most contribute to their success in different domains remains unclear. This uncertainty complicates LLM evaluation, as existing benchmark-based assessments often fail to capture their real-world performance, where the required capabilities may differ from those measured in the benchmarks. In this survey, we provide a systematic introduction to LLMs’ fundamental capabilities, encompassing their definitions, formation mechanisms, and practical applications. We further explore the relationships among these capabilities and discuss how they collectively support complex problem-solving in domain-specific applications. Building on this foundation, we review recent advances in LLM-driven applications across nine specific domains: medicine, law, computational biology, finance, social sciences and psychology, computer programming and software engineering, robots and agents, AI for disciplines, and creative work. We analyze how specific capabilities are leveraged for each domain to address unique requirements. This perspective enables us to establish connections between these capabilities and domain requirements, and to evaluate the varying importance of different capabilities across different domains. Based on these insights, we propose evaluation strategies tailored to the essential capabilities required in each domain, offering practical guidance for selecting suitable backbone LLMs in real-world applications.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"130 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting Misuse of Security APIs: A Systematic Review","authors":"Seyedehzahra Mosavi, Chadni Islam, Muhammad Ali Babar, Sharif Abuadbba, Kristen Moore","doi":"10.1145/3735968","DOIUrl":"https://doi.org/10.1145/3735968","url":null,"abstract":"Security Application Programming Interfaces (APIs) are crucial for ensuring software security. However, their misuse introduces vulnerabilities, potentially leading to severe data breaches and substantial financial loss. Complex API design, inadequate documentation, and insufficient security training often lead to unintentional misuse by developers. The software security community has devised and evaluated several approaches to detecting security API misuse to help developers and organizations. This study rigorously reviews the literature on detecting misuse of security APIs to gain a comprehensive understanding of this critical domain. Our goal is to identify and analyze security API misuses, the detection approaches developed, and the evaluation methodologies employed along with the open research avenues to advance the state-of-the-art in this area. Employing the systematic literature review (SLR) methodology, we analyzed 69 research papers. Our review has yielded (a) identification of 6 security API types; (b) classification of 30 distinct misuses; (c) categorization of detection techniques into heuristic-based and ML-based approaches; and (d) identification of 10 performance measures and 9 evaluation benchmarks. The review reveals a lack of coverage of detection approaches in several areas. We recommend that future efforts focus on aligning security API development with developers’ needs and advancing standardized evaluation methods for detection technologies.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"20 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cybersecurity Challenges in the EV Charging Ecosystem","authors":"Amanjot Kaur, Nima Valizadeh, Devki Nandan, Tomasz Szydlo, James R. K. Rajasekaran, Vijay Kumar, Mutaz Barika, Jun Liang, Rajiv Ranjan, Rana Omer","doi":"10.1145/3735662","DOIUrl":"https://doi.org/10.1145/3735662","url":null,"abstract":"The growing adoption of intelligent Electric Vehicles (EVs) has also created an opportunity for malicious actors to initiate attacks on the EV infrastructure, which can include a number of data exchange protocols across the various entities that are part of the EV charging ecosystem. These protocols possess a range of underlying vulnerabilities that attackers can exploit to disrupt the regular flow of information and energy. While researchers have considered vulnerabilities of particular components within an EV charging ecosystem, there is still a notable gap in vulnerability analysis of charging protocols and the potential threats to these. We investigate threat vectors within the most widely adopted protocols used in EV infrastructure, explore the potential impact of cyberattacks and suggest various mitigation techniques investigated in literature. Potential future research directions are also identified.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"78 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143980135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continual Learning of Large Language Models: A Comprehensive Survey","authors":"Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, Hao Wang","doi":"10.1145/3735633","DOIUrl":"https://doi.org/10.1145/3735633","url":null,"abstract":"The challenge of effectively and efficiently adapting statically pre-trained Large Language Models (LLMs) to ever-evolving data distributions remains predominant. When tailored for specific needs, pre-trained LLMs often suffer from significant performance degradation in previous knowledge domains – a phenomenon known as <jats:italic>“catastrophic forgetting”</jats:italic> . While extensively studied in the Continual Learning (CL) community, this problem presents new challenges in the context of LLMs. In this survey, we provide a comprehensive overview and detailed discussion of the current research progress on LLMs within the context of CL. Besides the introduction of the preliminary knowledge, this survey is structured into four main sections: we first describe an overview of continually learning LLMs, consisting of two directions of continuity: <jats:italic>vertical continuity (or vertical continual learning)</jats:italic> , i.e., continual adaptation from general to specific capabilities, and <jats:italic>horizontal continuity (or horizontal continual learning)</jats:italic> , i.e., continual adaptation across time and domains (Section 3). Following vertical continuity, we summarize three stages of learning LLMs in the context of modern CL: Continual Pre-Training (CPT), Domain-Adaptive Pre-training (DAP), and Continual Fine-Tuning (CFT) (Section 4). We then provide an overview of evaluation protocols for continual learning with LLMs, along with currently available data sources (Section 5). Finally, we discuss intriguing questions related to continual learning for LLMs (Section 6). This survey sheds light on the relatively understudied domain of continually pre-training, adapting, and fine-tuning large language models, suggesting the necessity for greater attention from the community. Key areas requiring immediate focus include the development of practical and accessible evaluation benchmarks, along with methodologies specifically designed to counter forgetting and enable knowledge transfer within the evolving landscape of LLM learning paradigms. The full list of papers examined in this survey is available at https://github.com/Wang-ML-Lab/llm-continual-learning-survey.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"36 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143980133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","authors":"Luís Vilaça, Yi Yu, Paula Viana","doi":"10.1145/3696445","DOIUrl":"https://doi.org/10.1145/3696445","url":null,"abstract":"Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data and can be observed in the number of proposals in the past years. Thus encouraging the development of a comprehensive survey. Besides analyzing the models used in this context, we also discuss some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate objective functions frequently used and discuss how audio-visual data is exploited in the optimization process, i.e., the different methodologies for representing knowledge in the audio-visual domain. In fact, we focus on how human-understandable mechanisms, i.e., structured knowledge that reflects comprehensible knowledge, can guide the learning process. Most importantly, we provide a summarization of the recent progress of Audio-Visual Correlation Learning (AVCL) and discuss the future research directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"124 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recent Advances in Symbolic Regression","authors":"Junlan Dong, Jinghui Zhong","doi":"10.1145/3735634","DOIUrl":"https://doi.org/10.1145/3735634","url":null,"abstract":"Symbolic regression (SR) is an optimization problem that identifies the most suitable mathematical expression or model to fit the observed dataset. Over the past decade, SR has experienced rapid development due to its interpretability and broad applicability, leading to numerous algorithms for addressing SR problems and a steady increase in practical applications. Given the lack of a comprehensive review of the current literature on SR and its significance to both academia and industry, this paper provides an in-depth overview of SR. The survey begins by outlining the background of SR and introducing it from three aspects: its definition, benchmarking datasets, and evaluation metrics. We also highlight the latest advancements in SR, summarizing the current research status. The review focuses on deterministic methods, genetic programming methods, and neural network methods, offering a thorough analysis of the advantages and limitations of various algorithms. Following this, key application scenarios of SR are introduced, and some commonly used software tools are summarized. Finally, the paper provides an outlook on future research directions. This survey reviews the latest developments in SR and offers insightful guidance for readers who are new to the field.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"43 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Literature Review on Neonatal Fingerprint Recognition","authors":"Luiz Fernando Puttow Southier, Gustavo Alexandre Tuchlinowicz Nunes, João Henrique Pereira Machado, Matheus Buratti, Pedro Henrique de Viveiros Trentin, Wesley Augusto Catuzzo de Bona, Barbara de Oliveira Koop, Elioenai Diniz, João Victor Costa Mazzochin, João Leonardo Harres Dall Agnol, Lucas Caldeira de Oliveira, Marcelo Filipak, Luiz Antonio Zanlorensi, Marcos Belançon, Jefferson Oliva, Marcelo Teixeira, Dalcimar Casanova","doi":"10.1145/3735551","DOIUrl":"https://doi.org/10.1145/3735551","url":null,"abstract":"Neonatal biometrics, especially those based on fingerprint traits, can potentially improve early childhood identification with decisive applications in healthcare, identity management, and other critical social domains. Although many biometric approaches to human recognition exist, most of them can not be directly applied to neonates. The main barrier is the reduced size of children’s biometric traits, which affects image quality as these traits are still developing. Another issue is the lack of child biometric databases, as a periodic recollection of images is a fundamental part of neonatal identification regarding the feasibility evaluation of temporal recognition. Several works can be found in the literature addressing some of these issues. However, there is still no systematic review allowing a general understanding of these solutions, discussing their links, gaps, comparisons, and open challenges. In this sense, this paper presents a systematic literature review on neonatal biometrics. In total, 1,878 papers were screened and classified, resulting in 45 being selected to be analyzed in this study. We detail and compare the results of datasets, scanners, methods, and techniques to achieve and improve neonatal recognition. Finally, research trends are identified and discussed based on the main gaps in the literature.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"109 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143930951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Distributed Data Deduplication for Big Data: A Survey","authors":"Yinjin Fu, Jun Su, Jiahao Ning, Jian Wu, Yutong Lu, Nong Xiao","doi":"10.1145/3735508","DOIUrl":"https://doi.org/10.1145/3735508","url":null,"abstract":"To address the throughput and capacity limitations of single-node centralized deduplication, distributed data deduplication has become a popular technology in big data management to save more storage space, enhance I/O performance, and improve system scalability. It includes inter-node data assignment from clients to multiple deduplication nodes by a data routing scheme, and independent intra-node redundancy suppression in individual nodes. In this paper, we first describe the background of big data deduplication. Then we summarize and classify the state-of-the-art in the key techniques of distributed data deduplication, including data partitioning, chunk fingerprinting, data routing, index lookup, data restoring, garbage collection, the security and reliability of deduplicated data. These help identify and understand the system implementation of the existing distributed data deduplication methods. Moreover, we present some representative industrial products that have successfully applied distributed data deduplication technologies. Finally, we discuss the main challenges and industry trend of distributed data deduplication, and outline the open problems and its future research directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"28 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143930952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}