Search

Explainable Artificial Intelligence (XAI) is a research area that clarifies AI decision-making processes to build user trust and promote responsible AI. Hence, a key scientific challenge in XAI is the development of methods that generate transparent and interpretable explanations while maintaining scalability and effectiveness in complex scenarios. Rule-based methods in XAI generate rules that can potentially explain AI inferences, yet they can also become convoluted in large scenarios, hindering their readability and scalability. Moreover, they often lack contrastive explanations, leaving users uncertain why specific predictions are preferred. To address this scientific problem, we explore the integration of computational argumentation—a sub-field of AI that models reasoning processes through defeasibility—into rule-based XAI systems. Computational argumentation enables arguments modelled from rules to be retracted based on new evidence. This makes it a promising approach to enhancing rule-based methods for creating more explainable AI systems. Nonetheless, research on their integration remains limited despite the appealing properties of rule-based systems and computational argumentation. Therefore, this study also addresses the applied challenge of implementing such an integration within practical AI tools. The study employs the Logic Learning Machine (LLM), a specific rule-extraction technique, and presents a modular design that integrates input rules into a structured argumentation framework using state-of-the-art computational argumentation methods. Experiments conducted on binary classification problems using various datasets from the UCI Machine Learning Repository demonstrate the effectiveness of this integration. The LLM technique excelled in producing a manageable number of if-then rules with a small number of premises while maintaining high inferential capacity for all datasets. In turn, argument-based models achieved comparable results to those derived directly from if-then rules, leveraging a concise set of rules and excelling in explainability. In summary, this paper introduces a novel approach for efficiently and automatically generating arguments and their interactions from data, addressing both scientific and applied challenges in advancing the application and deployment of argumentation systems in XAI.

Explainable Artificial Intelligence (XAI) is a research area that clarifies AI decision-making processes to build user trust and promote responsible AI. Hence, a key scientific challenge in XAI is the development of methods that generate transparent and interpretable explanations while maintaining scalability and effectiveness in complex scenarios. Rule-based methods in XAI generate rules that can potentially explain AI inferences, yet they can also become convoluted in large scenarios, hindering their readability and scalability. Moreover, they often lack contrastive explanations, leaving users uncertain why specific predictions are preferred. To address this scientific problem, we explore the integration of computational argumentation—a sub-field of AI that models reasoning processes through defeasibility—into rule-based XAI systems. Computational argumentation enables arguments modelled from rules to be retracted based on new evidence. This makes it a promising approach to enhancing rule-based methods for creating more explainable AI systems. Nonetheless, research on their integration remains limited despite the appealing properties of rule-based systems and computational argumentation. Therefore, this study also addresses the applied challenge of implementing such an integration within practical AI tools. The study employs the Logic Learning Machine (LLM), a specific rule-extraction technique, and presents a modular design that integrates input rules into a structured argumentation framework using state-of-the-art computational argumentation methods. Experiments conducted on binary classification problems using various datasets from the UCI Machine Learning Repository demonstrate the effectiveness of this integration. The LLM technique excelled in producing a manageable number of if-then rules with a small number of premises while maintaining high inferential capacity for all datasets. In turn, argument-based models achieved comparable results to those derived directly from if-then rules, leveraging a concise set of rules and excelling in explainability. In summary, this paper introduces a novel approach for efficiently and automatically generating arguments and their interactions from data, addressing both scientific and applied challenges in advancing the application and deployment of argumentation systems in XAI. [ABSTRACT FROM AUTHOR]

Cancellability – one of the most important tests for implicatures – has been attacked from different perspectives, and its reliability challenged by several cases and examples in which conversational implicatures seem to be hard or even impossible to cancel. To account for these phenomena, distinct approaches have been advanced aimed at weakening Grice's cancellability test. However, what do we exactly mean when we claim that an implicature cannot be cancelled? Grice pointed out that implicatures are triggered by a possible conflict with the cooperativeness principle, and for this reason it is always possible to opt out of the observation thereof. This theoretical possibility needs to be distinguished from the practical problem of explaining why some implicatures are intuitively less cancellable than others, or even not cancellable. To address this latter – practical – dimension of cancellability, the reasoning and the presumptive premises involved in drawing an implicature and justifying its cancellation needs to be represented and evaluated. This approach will be shown to provide a possible instrument for evaluating the reasonableness of cancellability and its costs. [ABSTRACT FROM AUTHOR]

It is often necessary and reasonable to justify preferences before reasoning from them. Moreover, justifying a preference ordering is reduced to justifying the criterion that produces the ordering. This paper builds on the well-known ASPIC+ formalism to develop a model that integrates justifying qualitative preferences with reasoning from the justified preferences. We first introduce a notion of preference criterion in order to model the way in which preferences are justified by an argumentation framework. We also adapt the notion of argumentation theory to build a sequence of argumentation frameworks, in which an argumentation framework justifies preferences that are to underlie the next framework. That is, in our formalism, preferences become not only an input of an argumentation framework, but also an output of it. This kind of input-output process can be applied in the further steps of argumentation. We also explore some interesting properties of our formalism. [ABSTRACT FROM AUTHOR]

Here I will develop a naturalistic account of epistemic reflection and its significance for epistemology. I will first argue that thought, as opposed to mere information processing, requires a capacity for cognitive self-regulation. After discussing the basic capacities necessary for cognitive self-regulation of any kind, I will consider qualitatively different kinds of thought that can emerge when the basic capacities enable the creature to interiorize a form of social cooperation. First, I will discuss second-personal cooperation and the kind of thought that emerges from its interiorization. Then, I will discuss third-personal cooperation and the kind of thought that emerges from its interiorization. We will see that epistemic reflection is the interiorized version of interpersonal argumentation, which is the epistemic component of third-personal cooperation. In developing this account, I will draw heavily on the work of Michael Tomasello and other cognitive scientists advocating the “social intentionality hypothesis”. However, I will show how work done in the defeasible reasoning tradition can provide us with a deeper explanation of some claims made by advocates of the social intentionality hypothesis. Additionally, we will see that work done on social intentionality can help us better understand the significance of knowledge and justification as understood by the defeasible reasoning tradition. We will see that the social intentionality hypothesis and the defeasible reasoning tradition are mutually illuminating. By drawing equally on both, I will provide a novel account of the foundations of knowledge. This account will be shown to retain the benefits of traditional foundationalism while also incorporating recent coherentist insights from work on the epistemology of scientific measurement. [ABSTRACT FROM AUTHOR]

Cancellability is an essential feature of implicatures. However, its reliability has been challenged by several cases and examples in which conversational implicatures seem to be hard or even impossible to cancel. Should it then be concluded that not all implicatures are cancellable, and therefore Grice's cancellability test should be weakened or abandoned? The present paper addresses this problem by drawing a distinction between theoretical and practical cancellability, where the latter concept captures the (un)reasonableness of explicit or contextual cancellation. By analyzing three legal cases of misleading advertising, I show how the indefensibility of an interpretation can account for the practical uncancellability of an implicature. To explain and account for the reasonableness of an interpretation, the presumptive inferences involved must be reconstructed and evaluated considering different dimensions, such as the conversational context and the associated presumptions. • Assessing the cancellability test. • Distinguishing between different dimensions of cancellability • Analyzing legal cases of misleading advertising. • Proposing an analytical method for justifying an interpretation. • Providing criteria for determining practical uncancellability [ABSTRACT FROM AUTHOR]

Sentences φ and ψ are cognitive synonyms for one when they play the same role in one's cognitive life. The notion is pervasive (Sect. 1), but elusive: it is bound to be hyperintensional (Sect. 2), but excessive fine-graining would trivialize it and there are reasons for some coarse-graining (Sect. 2.1). Conceptual limitations stand in the way of a natural algebra (Sect. 2.2), and it should be sensitive to subject matters (Sect. 2.3). A cognitively adequate individuation of content may be intransitive (Sect. 3) due to 'dead parrot' series: sequences of sentences φ 1 , ... , φ n where adjacent φ i and φ i + 1 are cognitive synonyms while φ 1 and φ n are not (Sect. 3.1). Finding an intransitive account is hard: Fregean equipollence won't do (Sect. 3.2) and a result by Leitgeb shows that it wouldn't satisfy a minimal compositionality principle (Sect. 3.3).Sed contra, there are reasons for transitivity, too (Sect. 3.4). In Sect. 4, we come up with a formal semantics capturing this jumble of desiderata, thereby showing that the notion is coherent. In Sect. 5, we re-assess the desiderata in its light. [ABSTRACT FROM AUTHOR]

I will discuss a variety of cases such that the subject's believing truly is somewhat of an accident, but less so than in a Gettier case. In each case, this is because her reasons are not ultimately undefeated full stop, but they are ultimately undefeated with certain qualifications. For example, the subject's reasons might be ultimately defeated considered in themselves but ultimately undefeated considered as a proper part of an inference to the best explanation that is undefeated without qualification. In each section of the paper, I consider different qualifications and show how in each case we get an epistemic standing I call "coach-class knowledge". First-class knowledge requires justifying reasons that are undefeated without qualification. Coach-class knowledge only requires qualified lack of defeat. I will use this distinction to bring debates over knowledge from falsehood and fake barns to an ecumenical resolution. In both cases, the subject enjoys coach-class rather than first-class knowledge. I will also show that the defeasible reasoning tradition can better account for graded accidental truth than safety theories. [ABSTRACT FROM AUTHOR]

There has been great confusion on Keynes's notions of probability and uncertainty in recent years. Keynes believes that probability (his logical probability) is the guide of life, i.e., it is having some reasons to believe and to act. So probability is a theory of reasonable partial belief and a logic of non-demonstrative reasoning, upon which decision and action in conditions of limited knowledge, are based. (His) probability is, for Keynes, a positive, constructive, and forward-looking element of life. Limited knowledge is not a bar to decision and action. According to him, (his) probability helps us in almost all ordinary situations of life. This is the main reason why Keynes believes that ignorance and uncertainty are the two most difficult issues to tackle in life and in economics in particular. Both are related to a lack of limited knowledge. Ignorance is a lack of known reasons; Keynes writes we do not know. Keynes's uncertainty is a much more intriguing concept than mere ignorance. Uncertainty is due to various reasons, one of them is the intrinsic incommensurability of probabilities. So, uncertainty is related to Keynes's philosophy of measurement, a philosophy that also pervades his complex economics. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the subject of the special issue Trends in Argumentation Logic. Here we mainly describe two approaches to argumentation logic with explicating monotonic and nonmonotonic, or defeasible, reasoning and explain the role of artificial intelligence in applying argumentation logic. Then we give a short overview of the papers contributed to the special issue. [ABSTRACT FROM AUTHOR]

Different formalisms for defeasible reasoning have been used to represent knowledge and reason in the legal field. In this work, we provide an overview of the following logic-based approaches to defeasible reasoning: defeasible logic, Answer Set Programming, ABA+, ASPIC+, and DeLP. We compare features of these approaches under three perspectives: the logical model (knowledge representation), the method (computational mechanisms), and the technology (available software resources). On top of that, two real examples in the legal domain are designed and implemented in ASPIC+ to showcase the benefit of an argumentation approach in real-world domains. The CrossJustice and Interlex projects are taken as a testbed, and experiments are conducted with the Arg2P technology.

Introduction: The paper investigates the impact of the use of metaphors in reasoning tasks concerning vaccination, especially for defeasible reasoning cases. We assumed that both metaphor and defeasible reasoning can be relevant to let people understand vaccination as an important collective health phenomenon, by anticipating possible defeating conditions. Methods: We hypothesized that extended metaphor could improve both the argumentative and the communicative effects of the message. We designed an empirical study to test our main hypotheses: participants (N = 196, 78% females; Meanage = 27.97 years, SDage = 10.40) were presented with a text about vaccination, described in either literal or metaphorical terms, based on uncertain vs. safe reasoning scenarios. Results: The results of the study confirmed that defeasible reasoning is relevant for the communicative impact of a text and that an extended metaphor enhances the overall communicative effects of the message, in terms of understandability, persuasion, perceived safety, and feeling of control over the health situation, collective trust in expertise and uptake of experts' advice. However, the results show that this effect is significantly nuanced by the type of defeasible reasoning, especially in the case of participants' trust in expertise and commitment to experts' advice. Conclusion: Both communicative and defeasible reasoning competences are needed to enhance trust in immunization, with possible different outcomes at an individual and collective level. [ABSTRACT FROM AUTHOR]

IntroductionThe paper investigates the impact of the use of metaphors in reasoning tasks concerning vaccination, especially for defeasible reasoning cases. We assumed that both metaphor and defeasible reasoning can be relevant to let people understand vaccination as an important collective health phenomenon, by anticipating possible defeating conditions.MethodsWe hypothesized that extended metaphor could improve both the argumentative and the communicative effects of the message. We designed an empirical study to test our main hypotheses: participants (N = 196, 78% females; Meanage = 27.97 years, SDage = 10.40) were presented with a text about vaccination, described in either literal or metaphorical terms, based on uncertain vs. safe reasoning scenarios.ResultsThe results of the study confirmed that defeasible reasoning is relevant for the communicative impact of a text and that an extended metaphor enhances the overall communicative effects of the message, in terms of understandability, persuasion, perceived safety, and feeling of control over the health situation, collective trust in expertise and uptake of experts' advice. However, the results show that this effect is significantly nuanced by the type of defeasible reasoning, especially in the case of participants' trust in expertise and commitment to experts' advice.ConclusionBoth communicative and defeasible reasoning competences are needed to enhance trust in immunization, with possible different outcomes at an individual and collective level.

The hypothesis-driven methodology is a cognitive activity used in expertise processes to solve problems with limited knowledge and understanding. Although some organizations have standardized this approach to guide humans in carrying out expertise in enterprises, it lacks appropriate tools to assist experts in carrying out this cognitive activity, tracking understanding, or capturing the reasoning steps and the knowledge produced during the process. To acquire, share and reuse experts' knowledge applied during expertise processes while assisting humans in bringing understanding to complex problems, this study introduces a human–machine collaborative framework that formalizes experts' knowledge from the hypothesis-driven methodology described in the France standard NF X50-110 of "Quality of expertise activity". This framework utilizes Hypothesis Theory extended with qualitative doubt and a systematic reasoning process to generate a hypothesis exploratory graph (HEG). The proposed approach makes it easier to carry out expertise processes through a human–machine collaboration, offers a means to share and reuse knowledge from expertise, and provides expertise processes evaluation mechanisms. Furthermore, an experiment conducted on a use-case of expertise process verifies the feasibility and effectiveness of the approach. [ABSTRACT FROM AUTHOR]

Introduction. This article focuses on the specifics of the arguments from ignorance and arguments from silence. The relevance of the work is due to the growing interest of the scientific community in modeling of defeasible (presumptive) reasoning and verification of their validity.Methodology and sources. Methodologically, the work is based on the dialectical approach of D. Walton, who proposed a corpus of argumentation schemes for presumptive arguments and a methodology for testing their validity using critical questions. To test the validity of arguments from ignorance and silence, we propose the concept of epistemic burden, the proper fulfillment of which is a necessary condition for the validity of these arguments.Results and discussion. The result of the research is the development of corpuses of critical questions for two schemes of argumentation: the argument for ignorance and the argument from silence, which include questions to check the fulfillment of the epistemic burden by the proponent or information source. The methodology for verifying arguments using the proposed critical questions is analyzed using examples.Conclusion. The difference between the two types of reasoning is that in the argument from ignorance, the epistemic burden is placed on the discussion participants (panelists), and in the argument from silence it is placed on the source of the information.

According to the Reasoning View, a normative reason to φ is a premise in a pattern of sound reasoning leading to the conclusion to φ. But how should the Reasoning View account for reasons that are outweighed? One very promising proposal is to appeal to defeasible reasoning. On this proposal, when a reason is outweighed, the associated pattern of sound reasoning is defeated. Both Jonathan Way and Sam Asarnow have recently developed this idea in different ways. I argue that this appeal to defeasible reasoning faces a challenge, since reasons can be both outweighed and disabled. Way's view generates good predictions about outweighed reasons, but not about disabled reasons. Asarnow's view generates good predictions about disabled reasons, but not about outweighed reasons. We want a version of the Reasoning View that can generate good predictions about both. I present a version of the Reasoning View that can meet the challenge. [ABSTRACT FROM AUTHOR]

Different formalisms for defeasible reasoning have been used to represent knowledge and reason in the legal field. In this work, we provide an overview of the following logic-based approaches to defeasible reasoning: defeasible logic, Answer Set Programming, ABA+, ASPIC+, and DeLP. We compare features of these approaches under three perspectives: the logical model (knowledge representation), the method (computational mechanisms), and the technology (available software resources). On top of that, two real examples in the legal domain are designed and implemented in ASPIC+ to showcase the benefit of an argumentation approach in real-world domains. The CrossJustice and Interlex projects are taken as a testbed, and experiments are conducted with the Arg2P technology. [ABSTRACT FROM AUTHOR]

The exact relationship between formal argumentation and nonmonotonic logics is a research topic that keeps on eluding researchers despite recent intensified efforts. We contribute to a deeper understanding of this relation by investigating characterizations of abstract dialectical frameworks in conditional logics for nonmonotonic reasoning. We first show that in general, there is a gap between argumentation and conditional semantics when applying several intuitive translations, but then prove that this gap can be closed when focusing on specific classes of translations. [ABSTRACT FROM AUTHOR]

Human conditional reasoning is defeasible: people withdrawlogically valid conclusions if they are aware of situations (i.e.,exceptions) that prevent the consequent of the rule to happenalthough the antecedent is given. In this paper we investigatedefeasible reasoning with quantified rules. In two experimentswe rephrased conditionals from the literature (Experiment 1)and rules from penal code (Experiment 2) as either universalor existential rules and embedded them into Modus Ponensand Modus Tollens inference problems. We show that defeasiblereasoning also exists for quantified rules. However, thekind of quantifier (universal vs. existential) did not affect inferences.This last finding conflicts with theories highlightingthe importance of logic in human reasoning.

We extend universal moral grammar theory (UMGT) with nonmonotoniclogic. Our experiment shows that such revision isnecessary as it allows to account for the effects of alleviationsand aggravations in moral reasoning. Our new theory updatesUMGT from classical to non-monotonic logic, which reflectsthe incompleteness of information and uncertainty in actualhuman reasoning. In addition, it provides an explanation ofthe paradoxical findings in the moral dilemma of the Trolleyproblem and the Knobe effect

The paper investigates the epistemological and communicative competences the experts need to use and communicate evidence in the reasoning process leading to diagnosis. The diagnosis and diagnosis communication are presented as intertwined processes that should be jointly addressed in medical consultations, to empower patients' compliance in illness management. The paper presents defeasible reasoning as specific to the diagnostic praxis, showing how this type of reasoning threatens effective diagnosis communication and entails that we should understand diagnostic evidence as defeasible as well. It argues that metaphors might be effective communicative devices to let the patients understand the relevant defeasors in the diagnostic reasoning process, helping to improve effective diagnosis communication, and also encouraging a change in patients' beliefs and attitudes on their own experience of illness and illness' management. [ABSTRACT FROM AUTHOR]

The study of defeasible reasoning unites epistemologists with those working in AI, in part, because both are interested in epistemic rationality. While it is traditionally thought to govern the formation and (with)holding of beliefs, epistemic rationality may also apply to the interrogative attitudes associated with our core epistemic practice of inquiry, such as wondering, investigating, and curiosity. Since generally intelligent systems should be capable of rational inquiry, AI researchers have a natural interest in the norms that govern interrogative attitudes. Following its recent coinage, we use the term "zetetic" to refer to the properties and norms associated with the capacity to inquire. In this paper, we argue that zetetic norms can be modeled via defeasible inferences to and from questions -- a.k.a erotetic inferences -- in a manner similar to the way norms of epistemic rationality are represented by defeasible inference rules. We offer a sequent calculus that accommodates the unique features of "erotetic defeat" and that exhibits the computational properties needed to inform the design of zetetic agents. The calculus presented here is an improved version of the one presented in (Millson, 2019), extended to cover a new class of defeasible erotetic inferences. [ABSTRACT FROM AUTHOR]