Explanation in Case-Based Reasoning–Perspectives and Goals

By Frode Sørmo, Jörg Cassens, Agnar Aamodt. 2005

285 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Knowledge Graphs & Representation

Citations in the corpus

The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning (2019, background): “For example, there are clearly limits to the use of cases as explanations, that can be meaningfully understood by users based on their expertise of a domain or limitedcapacity processing [Sørmo et al., 2005].”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “…and Díez, 2002; Miller, 2017; Miller, Howe, and Sonenberg, 2017; Miller et al., 2017; Moore and Swartout, 1988; Moulin, Irandoust, Bélanger, and Desbordes, 2002; Mueller and Klein, 2011; Sørmo, Cassens, and Aamodt, 2005; Swartout and Moore, 1993; Weston et al., 2015; Wick and Thompson, 1992).”
The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification (2014, background): “CBR has been used in important real-world applications [24, 4], but is fundamentally limited, in that it does not learn the underlying complex structure of data in an unsupervised fashion and may not scale to datasets with high-dimensional feature spaces (as discussed in [29]).”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “2 There is a large number of surveys that provide an overview of explanations published elsewhere (Tintarev and Masthoff 2007b, 2011; Swartout and Moore 1993; Chandrasekaran et al. 1989; Dhaliwal and Benbasat 1996; Gregor and Benbasat 1999; Moulin et al. 2002; Lacave and Díez 2002, 2004; Sørmo et al”
Retrieval, reuse, revision and retention in case-based reasoning (2005, unknown): “Explanations serve many different goals, such as teaching the user about the domain or explaining the relevance of a question the user is asked (Leake, 1991, 1992;Sørmo & Cassens, 2004;Sørmo et al., 2005).”
A Survey of Explanations in Recommender Systems (2007, background): “Explanations should be part of a cycle, where the user understands what is going on in the system and exerts control over the type of recommendations made, by correcting system assumptions where needed [ 32 ].”
Explanatory Capabilities in the CREEK Knowledge-Intensive Case-Based Reasoner (2008, background): “We have previously presented a framework for explanations in intelligent systems with a special focus on case-based reasoning [2].”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “One of these studies presented an overview of different theories of explanation borrowed from the cognitive science and philosophy disciplines, contextualised within case-based reasoning [35].”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, unknown): “Later research focused on explaining Bayesian Belief Networks [102, 126] and CaseBase Reasoning systems [159], following the trends of research interest in these AI paradigms.”
Gaining insight through case-based explanation (2009, background): “explanations are domain and user dependent (Sormo et al., 2005), and this should be reflected in the case retrieval process.”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “This approach is also claimed to set a minimum criterion that an explanation must fulﬁll: it must favor the probability of the observed event P to all the hypothetical alternatives ( Q 1 , Q 2 , . . . , Q n ) [14].”
A Case-Based Explanation System for Black-Box Systems (2005, background): “The exact form of the explanation and what information is presented to the user is very much both task and domain dependent (Cassens, 2004; Sørmo et al., 2005).”
Interactive and interpretable machine learning models for human machine collaboration (2015, background): “CBR has been used in important real-world applications [91, 19], but it does not learn the underlying complex structure of data in an unsupervised fashion and may not scale to datasets with high-dimensional feature spaces (as discussed in [123]).”
How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, background): “CBR systems are notable in this respect, through their use of examples/cases/precedents to explain system outputs [7, 10, 11, 12, 18, 19].”
Designing and Evaluating Explanations for Recommender Systems (2011, background): “Explanations should be part of a cycle, where the user understands what is going on in the system and exerts control over the type of recommendations made, by correcting system assumptions where needed [56].”