2000 character limit reached
Generating Context-Aware Contrastive Explanations in Rule-based Systems (2402.13000v1)
Published 20 Feb 2024 in cs.SE
Abstract: Human explanations are often contrastive, meaning that they do not answer the indeterminate "Why?" question, but instead "Why P, rather than Q?". Automatically generating contrastive explanations is challenging because the contrastive event (Q) represents the expectation of a user in contrast to what happened. We present an approach that predicts a potential contrastive event in situations where a user asks for an explanation in the context of rule-based systems. Our approach analyzes a situation that needs to be explained and then selects the most likely rule a user may have expected instead of what the user has observed. This contrastive event is then used to create a contrastive explanation that is presented to the user. We have implemented the approach as a plugin for a home automation system and demonstrate its feasibility in four test scenarios.
- Ankit Agrawal and Jane Cleland-Huang. 2021. Explaining Autonomous Decisions in Swarms of Human-on-the-Loop Small Unmanned Aerial Systems. AAAI Conference on Human Computation and Crowdsourcing 9 (2021), 15–26. https://doi.org/10.1609/hcomp.v9i1.18936
- A review of smart homes—Past, present, and future. IEEE Transactions on Systems, Man, and Cybernetics, part C (applications and reviews) 42, 6 (2012), 1190––1203. https://doi.org/10.1109/tsmcc.2012.2189204
- Contrastive Explanations for Explaining Model Adaptations. Springer International Publishing, 101––112. https://doi.org/10.1007/978-3-030-85030-2_9
- Towards Self-Explainable Cyber-Physical Systems. In ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C). IEEE. https://doi.org/10.1109/models-c.2019.00084
- Quo Vadis, Explainability? – A Research Roadmap for Explainability Engineering. Springer International Publishing, 26––32. https://doi.org/10.1007/978-3-030-98464-9_3
- Larissa Chazette and Kurt Schneider. 2020. Explainability as a non-functional requirement: challenges and recommendations. Requirements Engineering 25, 4 (2020), 493––514. https://doi.org/10.1007/s00766-020-00333-1
- KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference. In 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.196
- The Effect of Explanation Design on User Perception of Smart Home Lighting Systems: A Mixed-method Investigation. In CHI Conference on Human Factors in Computing Systems. ACM. https://doi.org/10.1145/3544548.3581263
- Towards Self-Explaining Digital Systems: A Design Methodology for the Next Generation. In IEEE 3rd International Verification and Security Workshop (IVSW). IEEE. https://doi.org/10.1109/ivsw.2018.8494900
- Smart Environments Concepts, Applications, and Challenges. Springer International Publishing, 493––519. https://doi.org/10.1007/978-3-030-59338-4_24
- Juliana J. Ferreira and Mateus S. Monteiro. 2020. What Are People Doing About XAI User Experience? A Survey on AI Explainability Research and Practice. Springer International Publishing, 56––73. https://doi.org/10.1007/978-3-030-49760-6_4
- Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots. In Explainable Robotic Systems Workshop (HRI). https://doi.org/10.48550/arXiv.1803.02088
- A generic and modular reference architecture for self-explainable smart homes. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS). IEEE.
- A new approach for multiple objective decision making. Computers & operations research 20, 8 (1993).
- Contrastive explanations for model interpretability. arXiv preprint arXiv:2103.01378 (2021).
- David Lewis. 1986. Causal Explanation. In Philosophical Papers Vol. Ii, David Lewis (Ed.). Oxford University Press, 214–240.
- Questioning the AI: informing design practices for explainable AI user experiences. In CHI conference on human factors in computing systems.
- Why and why not explanations improve the intelligibility of context-aware intelligent systems. In SIGCHI conference on human factors in computing systems.
- Peter Lipton. 1990. Contrastive explanation. Royal Institute of Philosophy Supplements 27 (1990).
- Tim Miller. 2019. Explanation in artificial intelligence: Insights from the social sciences. Artificial intelligence 267 (2019).
- Tim Miller. 2021. Contrastive explanation: A structural-model approach. The Knowledge Engineering Review 36 (2021).
- Chandrakana Nandi and Michael D Ernst. 2016. Automatic trigger generation for rule-based smart homes. In ACM Workshop on Programming Languages and Analysis for Security.
- David L Olson. 2004. Comparison of weights in TOPSIS models. Mathematical and Computer Modelling 40, 7 (2004).
- Explaining Cyber-Physical Systems Using Decision Trees. In 2nd International Workshop on Computation-Aware Algorithmic Design for Cyber-Physical Systems (CAADCPS). IEEE. https://doi.org/10.1109/caadcps56132.2022.00006
- User requirements for the design of smart homes: dimensions and goals. Journal of Ambient Intelligence and Humanized Computing (2022).
- Neal J Roese. 1997. Counterfactual thinking. Psychological bulletin 121, 1 (1997).
- SmartEx: A Framework for Generating User-Centric Explanations in Smart Environments. In IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE.
- Cases for Explainable Software Systems: Characteristics and Examples. In IEEE 29th International Requirements Engineering Conference Workshops (REW). https://doi.org/10.1109/REW53955.2021.00033
- A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access 9 (2021).
- Michael Winikoff. 2018. Towards trusting autonomous systems. In 5th International Workshop on Engineering Multi-Agent Systems (EMAS 2017). Springer.
- Application of TOPSIS method for decision making. IJSRMSS International Journal of Scientific Research in Mathematical and Statistical Sciences (2020).
- Lars Herbold (2 papers)
- Mersedeh Sadeghi (5 papers)
- Andreas Vogelsang (43 papers)