Artificial Intelligence最新文献

{"title":"(Re)Conceptualizing trustworthy AI: A foundation for change","authors":"Christopher D. Wirz ,&nbsp;Julie L. Demuth ,&nbsp;Ann Bostrom ,&nbsp;Mariana G. Cains ,&nbsp;Imme Ebert-Uphoff ,&nbsp;David John Gagne II ,&nbsp;Andrea Schumacher ,&nbsp;Amy McGovern ,&nbsp;Deianna Madlambayan","doi":"10.1016/j.artint.2025.104309","DOIUrl":"10.1016/j.artint.2025.104309","url":null,"abstract":"<div><div>Developers and academics have grown increasingly interested in developing “trustworthy” artificial intelligence (AI). However, this aim is difficult to achieve in practice, especially given trust and trustworthiness are complex, multifaceted concepts that cannot be completely guaranteed nor built entirely into an AI system. We have drawn on the breadth of trust-related literature across multiple disciplines and fields to synthesize knowledge pertaining to interpersonal trust, trust in automation, and risk and trust. Based on this review we have (re)conceptualized trustworthiness in practice as being both (a) perceptual, meaning that a user assesses whether, when, and to what extent AI model output is trustworthy, even if it has been developed in adherence to AI trustworthiness standards, and (b) context-dependent, meaning that a user's perceived trustworthiness and use of an AI model can vary based on the specifics of their situation (e.g., time-pressures for decision-making, high-stakes decisions). We provide our reconceptualization to nuance how trustworthiness is thought about, studied, and evaluated by the AI community in ways that are more aligned with past theoretical research.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"342 ","pages":"Article 104309"},"PeriodicalIF":5.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stochastic population update can provably be helpful in multi-objective evolutionary algorithms","authors":"Chao Bian ,&nbsp;Yawen Zhou ,&nbsp;Miqing Li ,&nbsp;Chao Qian","doi":"10.1016/j.artint.2025.104308","DOIUrl":"10.1016/j.artint.2025.104308","url":null,"abstract":"<div><div>Evolutionary algorithms (EAs) have been widely and successfully applied to solve multi-objective optimization problems, due to their nature of population-based search. Population update, a key component in multi-objective EAs (MOEAs), is usually performed in a greedy, deterministic manner. That is, the next-generation population is formed by selecting the best solutions from the current population and newly-generated solutions (irrespective of the selection criteria used such as Pareto dominance, crowdedness and indicators). In this paper, we analytically present that stochastic population update can be beneficial for the search of MOEAs. Specifically, we prove that the expected running time of two well-established MOEAs, SMS-EMOA and NSGA-II, for solving two bi-objective problems, OneJumpZeroJump and bi-objective RealRoyalRoad, can be exponentially decreased if replacing its deterministic population update mechanism by a stochastic one. Empirical studies also verify the effectiveness of the proposed population update method. This work is an attempt to show the benefit of introducing randomness into the population update of MOEAs. Its positive results, which might hold more generally, should encourage the exploration of developing new MOEAs in the area.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104308"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Grounded predictions of teamwork as a one-shot game: A multiagent multi-armed bandits approach","authors":"Alejandra López de Aberasturi Gómez,&nbsp;Carles Sierra,&nbsp;Jordi Sabater-Mir","doi":"10.1016/j.artint.2025.104307","DOIUrl":"10.1016/j.artint.2025.104307","url":null,"abstract":"<div><div>Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner's theory of group productivity. We characterise this novel game's Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty influence agents' strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating findings from social psychology research.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104307"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Grammar induction from visual, speech and text","authors":"Yu Zhao ,&nbsp;Hao Fei ,&nbsp;Shengqiong Wu ,&nbsp;Meishan Zhang ,&nbsp;Min Zhang ,&nbsp;Tat-seng Chua","doi":"10.1016/j.artint.2025.104306","DOIUrl":"10.1016/j.artint.2025.104306","url":null,"abstract":"<div><div>Grammar Induction (GI) seeks to uncover the underlying grammatical rules and linguistic patterns of a language, positioning it as a pivotal research topic within Artificial Intelligence (AI). Although extensive research in GI has predominantly focused on text or other singular modalities, we reveal that GI could significantly benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complementary roles to each other. With such intuition, this work introduces a novel <em>unsupervised visual-audio-text grammar induction</em> task (named <strong>VAT-GI</strong>), to induce the constituent grammar trees from parallel images, text, and speech inputs. Inspired by the fact that language grammar natively exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. Thus we further introduce a <em>textless</em> setting of VAT-GI, wherein the task solely relies on visual and auditory inputs. To approach the task, we propose a visual-audio-text inside-outside recursive autoencoder (<strong>VaTiora</strong>) framework, which leverages rich modal-specific and complementary features for effective grammar parsing. Besides, a more challenging benchmark data is constructed to assess the generalization ability of VAT-GI system. Experiments on two benchmark datasets demonstrate that our proposed VaTiora system is more effective in incorporating the various multimodal signals, and also presents new state-of-the-art performance of VAT-GI. Further in-depth analyses are shown to gain a deep understanding of the VAT-GI task and how our VaTiora system advances. Our code and data: <span><span>https://github.com/LLLogen/VAT-GI/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104306"},"PeriodicalIF":5.1,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143418533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the computation of mixed strategies for security games with general defending requirements","authors":"Rufan Bai ,&nbsp;Haoxing Lin ,&nbsp;Xiaowei Wu ,&nbsp;Minming Li ,&nbsp;Weijia Jia","doi":"10.1016/j.artint.2025.104297","DOIUrl":"10.1016/j.artint.2025.104297","url":null,"abstract":"<div><div>The Stackelberg security game is played between a defender and an attacker, where the defender needs to allocate a limited amount of resources to multiple targets in order to minimize the loss due to adversarial attacks by the attacker. While allowing targets to have different values, classic settings often assume uniform requirements for defending the targets. This enables existing results that study mixed strategies (randomized allocation algorithms) to adopt a <em>compact representation</em> of the mixed strategies.</div><div>In this work, we initiate the study of mixed strategies for security games in which the targets can have different defending requirements. In contrast to the case of uniform defending requirements, for which an optimal mixed strategy can be computed efficiently, we show that computing the optimal mixed strategy is <span>NP</span>-hard for the general defending requirements setting. However, we show strong upper and lower bounds for the optimal mixed strategy defending result. Additionally, we extend our analysis to study uniform attack settings on these security games.</div><div>We propose an efficient close-to-optimal <span>Patching</span> algorithm that computes mixed strategies using only a few pure strategies. Furthermore, we study the setting when the game is played on a network and resource sharing is enabled between neighboring targets. We show the effectiveness of our algorithm in various large real-world datasets, addressing both uniform and general defending requirements.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104297"},"PeriodicalIF":5.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"IID prophet inequality with a single data point","authors":"Yilong Feng ,&nbsp;Bo Li ,&nbsp;Haolong Li ,&nbsp;Xiaowei Wu ,&nbsp;Yutong Wu","doi":"10.1016/j.artint.2025.104296","DOIUrl":"10.1016/j.artint.2025.104296","url":null,"abstract":"<div><div>In this work, we study the single-choice prophet inequality problem, where a seller encounters a sequence of <em>n</em> online bids. These bids are modeled as independent and identically distributed (i.i.d.) random variables drawn from an unknown distribution. Upon the revelation of each bid's value, the seller must make an immediate and irrevocable decision on whether to accept the bid and sell the item to the bidder. The objective is to maximize the competitive ratio between the expected gain of the seller and that of the maximum bid. It is shown by Correa et al. <span><span>[1]</span></span> that when the distribution is unknown or only <span><math><mi>o</mi><mo>(</mo><mi>n</mi><mo>)</mo></math></span> uniform samples from the distribution are given, the best an algorithm can do is <span><math><mn>1</mn><mo>/</mo><mi>e</mi></math></span>-competitive. In contrast, when the distribution is known <span><span>[2]</span></span>, or when <span><math><mi>Ω</mi><mo>(</mo><mi>n</mi><mo>)</mo></math></span> uniform samples are given <span><span>[3]</span></span>, the optimal competitive ratio of 0.7451 can be achieved. In this paper, we study the setting when the seller has access to a single point in the cumulative density function of the distribution, which can be learned from historical sales data. We investigate how effectively this data point can be used to design competitive algorithms. Motivated by the algorithm for the secretary problem, we propose the observe-and-accept algorithm that sets a threshold in the first phase using the data point and adopts the highest bid from the first phase as the threshold for the second phase. It can be viewed as a natural combination of the single-threshold algorithm for prophet inequality and the secretary problem algorithm. We show that our algorithm achieves a good competitive ratio for a wide range of data points, reaching up to 0.6785-competitive as <span><math><mi>n</mi><mo>→</mo><mo>∞</mo></math></span> for certain data points. Additionally, we study an extension of the algorithm that utilizes more than two phases and show that the competitive ratio can be further improved to at least 0.6862.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104296"},"PeriodicalIF":5.1,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Explanations for query answers under existential rules","authors":"İsmail İlkan Ceylan ,&nbsp;Thomas Lukasiewicz ,&nbsp;Enrico Malizia ,&nbsp;Andrius Vaicenavičius","doi":"10.1016/j.artint.2025.104294","DOIUrl":"10.1016/j.artint.2025.104294","url":null,"abstract":"<div><div>Ontology-based data access is an extensively studied paradigm aiming at improving query answers with the use of an “ontology”. An ontology is a specification of a domain of interest, which, in this context, is described via a logical theory. As a form of logical entailment, ontology-mediated query answering is fully interpretable, which makes it possible to derive explanations for ontological query answers. This is a quite important aspect, as the fact that many recent AI systems mostly operating as black boxes has led to some serious concerns. In the literature, various works on explanations in the context of description logics (DLs) have appeared, mostly focusing on explaining concept subsumption and concept unsatisfiability in the ontologies. Some works on explaining query entailment in DLs have appeared as well, however, mainly dealing with inconsistency-tolerant semantics and, actually, <em>non</em>-entailment of the queries. Surprisingly, explaining ontological query entailment has received little attention for ontology languages based on existential rules. In fact, although DLs are popular formalisms to model ontologies, it is generally agreed that rule-based ontologies are well-suited for data-intensive applications, as they allow us to conveniently deal with higher-arity relations, which naturally occur in standard relational databases. The goal of this work is to close this gap, and study the problem of explaining query entailment in the context of existential rules ontologies in terms of minimal subsets of database facts. We provide a thorough complexity analysis for several decision problems associated with minimal explanations for various classes of existential rules, and for different complexity measures.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104294"},"PeriodicalIF":5.1,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"No free lunch theorem for privacy-preserving LLM inference","authors":"Xiaojin Zhang ,&nbsp;Yahao Pang ,&nbsp;Yan Kang ,&nbsp;Wei Chen ,&nbsp;Lixin Fan ,&nbsp;Hai Jin ,&nbsp;Qiang Yang","doi":"10.1016/j.artint.2025.104293","DOIUrl":"10.1016/j.artint.2025.104293","url":null,"abstract":"<div><div>Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable tasks. Furthermore, LLMs possess the capacity to sift through extensive datasets, uncover underlying patterns, and furnish critical insights that propel the frontiers of technology and science. However, LLMs also pose privacy concerns. Users' interactions with LLMs may expose their sensitive personal or company information. A lack of robust privacy safeguards and legal frameworks could permit the unwarranted intrusion or improper handling of individual data, thereby risking infringements of privacy and the theft of personal identities. To ensure privacy, it is essential to minimize the dependency between shared prompts and private information. Various randomization approaches have been proposed to protect prompts' privacy, but they may incur utility loss compared to unprotected LLMs prompting. Therefore, it is essential to evaluate the balance between the risk of privacy leakage and loss of utility when conducting effective protection mechanisms. The current study develops a framework for inferring privacy-protected Large Language Models (LLMs) and lays down a solid theoretical basis for examining the interplay between privacy preservation and utility. The core insight is encapsulated within a theorem that is called as the NFL (abbreviation of the word No-Free-Lunch) Theorem.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104293"},"PeriodicalIF":5.1,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 Kripke-Lewis semantics for belief update and belief revision","authors":"Giacomo Bonanno","doi":"10.1016/j.artint.2024.104259","DOIUrl":"10.1016/j.artint.2024.104259","url":null,"abstract":"<div><div>We provide a new characterization of both belief update and belief revision in terms of a Kripke-Lewis semantics. We consider frames consisting of a set of states, a Kripke belief relation and a Lewis selection function. Adding a valuation to a frame yields a model. Given a model and a state, we identify the initial belief set <em>K</em> with the set of formulas that are believed at that state and we identify either the updated belief set <span><math><mi>K</mi><mo>⋄</mo><mi>ϕ</mi></math></span> or the revised belief set <span><math><mi>K</mi><mo>⁎</mo><mi>ϕ</mi></math></span> (prompted by the input represented by formula <em>ϕ</em>) as the set of formulas that are the consequent of conditionals that (1) are believed at that state and (2) have <em>ϕ</em> as antecedent. We show that this class of models characterizes both the Katsuno-Mendelzon (KM) belief update functions and the Alchourrón, Gärdenfors and Makinson (AGM) belief revision functions, in the following sense: (1) each model gives rise to a partial belief function that can be completed into a full KM/AGM update/revision function, and (2) for every KM/AGM update/revision function there is a model whose associated belief function coincides with it. The difference between update and revision can be reduced to two semantic properties that appear in a stronger form in revision relative to update, thus confirming the finding by Peppas et al. (1996) <span><span>[30]</span></span> that, “for a fixed theory <em>K</em>, revising <em>K</em> is much the same as updating <em>K</em>”. It is argued that the proposed semantic characterization brings into question the common interpretation of belief revision and update as change in beliefs in response to new information.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"339 ","pages":"Article 104259"},"PeriodicalIF":5.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EMOA*: A framework for search-based multi-objective path planning","authors":"Zhongqiang Ren ,&nbsp;Carlos Hernández ,&nbsp;Maxim Likhachev ,&nbsp;Ariel Felner ,&nbsp;Sven Koenig ,&nbsp;Oren Salzman ,&nbsp;Sivakumar Rathinam ,&nbsp;Howie Choset","doi":"10.1016/j.artint.2024.104260","DOIUrl":"10.1016/j.artint.2024.104260","url":null,"abstract":"<div><div>In the Multi-Objective Shortest Path Problem (MO-SPP), one has to find paths on a graph that simultaneously minimize multiple objectives. It is not guaranteed that there exists a path that minimizes all objectives, and the problem thus aims to find the set of Pareto-optimal paths from the start to the goal vertex. A variety of multi-objective A*-based search approaches have been developed for this purpose. Typically, these approaches maintain a front set at each vertex during the search process to keep track of the Pareto-optimal paths that reach that vertex. Maintaining these front sets becomes burdensome and often slows down the search when there are many Pareto-optimal paths. In this article, we first introduce a framework for MO-SPP with the key procedures related to the front sets abstracted and highlighted, which provides a novel perspective for understanding the existing multi-objective A*-based search algorithms. Within this framework, we develop two different, yet closely related approaches to maintain these front sets efficiently during the search. We show that our approaches can find all cost-unique Pareto-optimal paths, and analyze their runtime complexity. We implement the approaches and compare them against baselines using instances with three, four and five objectives. Our experimental results show that our approaches run up to an order of magnitude faster than the baselines.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"339 ","pages":"Article 104260"},"PeriodicalIF":5.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}