More Like this

1. Advancements in xASP, an XAI System for Answer Set Programming

   Mario Alviano, Ly Ly (June 2023, CEUR-WS.org)

   Agostino Dovier, Andrea Formisano (Ed.)

   Explainable artificial intelligence (XAI) aims at addressing complex problems by coupling solutions with reasons that justify the provided answer. In the context of Answer Set Programming (ASP) the user may be interested in linking the presence or absence of an atom in an answer set to the logic rules involved in the inference of the atom. Such explanations can be given in terms of directed acyclic graphs (DAGs). This article reports on the advancements in the development of the XAI system xASP by revising the main foundational notions and by introducing new ASP encodings to compute minimal assumption sets, explanation sequences, and explanation DAGs. 

   more » « less
2. Abstraction, validation , and generalization for explainable artificial intelligence

   https://doi.org/10.1002/ail2.37  

   Yang, Scott Cheng‐Hsin; Folke, Tomas; Shafto, Patrick (September 2021, Applied AI Letters)

   Abstract Neural network architectures are achieving superhuman performance on an expanding range of tasks. To effectively and safely deploy these systems, their decision‐making must be understandable to a wide range of stakeholders. Methods to explain artificial intelligence (AI) have been proposed to answer this challenge, but a lack of theory impedes the development of systematic abstractions, which are necessary for cumulative knowledge gains. We propose Bayesian Teaching as a framework for unifying explainable AI (XAI) by integrating machine learning and human learning. Bayesian Teaching formalizes explanation as a communication act of an explainer to shift the beliefs of an explainee. This formalization decomposes a wide range of XAI methods into four components: (a) the target inference, (b) the explanation, (c) the explainee model, and (d) the explainer model. The abstraction afforded by Bayesian Teaching to decompose XAI methods elucidates the invariances among them. The decomposition of XAI systems enables modular validation, as each of the first three components listed can be tested semi‐independently. This decomposition also promotes generalization through recombination of components from different XAI systems, which facilitates the generation of novel variants. These new variants need not be evaluated one by one provided that each component has been validated, leading to an exponential decrease in development time. Finally, by making the goal of explanation explicit, Bayesian Teaching helps developers to assess how suitable an XAI system is for its intended real‐world use case. Thus, Bayesian Teaching provides a theoretical framework that encourages systematic, scientific investigation of XAI. 

   more » « less
3. An Application of ASP in Nuclear Engineering: Explaining the Three Mile Island Nuclear Accident Scenario

   https://doi.org/10.1017/S1471068420000241  

   HANNA, BOTROS N.; TRIEU, LY LY; SON, TRAN C.; DINH, NAM T. (November 2020, Theory and Practice of Logic Programming)

   null (Ed.)

   Abstract The paper describes an ongoing effort in developing a declarative system for supporting operators in the Nuclear Power Plant (NPP) control room. The focus is on two modules: diagnosis and explanation of events that happened in NPPs. We describe an Answer Set Programming (ASP) representation of an NPP, which consists of declarations of state variables, components, their connections, and rules encoding the plant behavior. We then show how the ASP program can be used to explain the series of events that occurred in the Three Mile Island, Unit 2 (TMI-2) NPP accident, the most severe accident in the USA nuclear power plant operating history. We also describe an explanation module aimed at addressing answers to questions such as “why an event occurs?” or “what should be done?” given the collected data. 

   more » « less
4. Beyond NP: Quantifying over Answer Sets

   https://doi.org/10.1017/S1471068419000140  

   AMENDOLA, GIOVANNI; RICCA, FRANCESCO; TRUSZCZYNSKI, MIROSLAW (September 2019, Theory and Practice of Logic Programming)

   Abstract Answer Set Programming (ASP) is a logic programming paradigm featuring a purely declarative language with comparatively high modeling capabilities. Indeed, ASP can model problems in NP in a compact and elegant way. However, modeling problems beyond NP with ASP is known to be complicated, on the one hand, and limited to problems in $$\[\Sigma _2^P\]$$ on the other. Inspired by the way Quantified Boolean Formulas extend SAT formulas to model problems beyond NP, we propose an extension of ASP that introduces quantifiers over stable models of programs. We name the new language ASP with Quantifiers (ASP(Q)). In the paper we identify computational properties of ASP(Q); we highlight its modeling capabilities by reporting natural encodings of several complex problems with applications in artificial intelligence and number theory; and we compare ASP(Q) with related languages. Arguably, ASP(Q) allows one to model problems in the Polynomial Hierarchy in a direct way, providing an elegant expansion of ASP beyond the class NP. 

   more » « less
5. Modular Answer Set Programming as a Formal Specification Language

   https://doi.org/10.1017/S1471068420000265  

   CABALAR, PEDRO; FANDINNO, JORGE; LIERLER, YULIYA (September 2020, Theory and Practice of Logic Programming)

   null (Ed.)

   Abstract In this paper, we study the problem of formal verification for Answer Set Programming (ASP), namely, obtaining a formal proof showing that the answer sets of a given (non-ground) logic program P correctly correspond to the solutions to the problem encoded by P , regardless of the problem instance. To this aim, we use a formal specification language based on ASP modules, so that each module can be proved to capture some informal aspect of the problem in an isolated way. This specification language relies on a novel definition of (possibly nested, first order) program modules that may incorporate local hidden atoms at different levels. Then, verifying the logic program P amounts to prove some kind of equivalence between P and its modular specification. 

   more » « less