Hierarchical Expertise Level Modeling for User Specific Contrastive Explanations
Open accessAbstract
There is a growing interest within the AI research community in developing autonomous systems capable of explaining their behavior to users. However, the problem of computing explanations for users of different levels of expertise has received little research attention. We propose an approach for addressing this problem by representing the user's understanding of the task as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating an explanation to a search over the space of abstract models and show that while the complete problem is NP-hard, a greedy algorithm can provide good approximations of the optimal solution. We also empirically show that our approach can efficiently compute explanations for a variety of problems.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Counterfactuals describe events or states of the world that did not occur and implicitly or explicitly contradict factual world knowledge.
“Counterfactuals describe events or states of the world that did not occur and implicitly or explicitly contradict factual world knowledge [27].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A Formal Basis for the Heuristic Determination of Minimum Cost Paths
Hart, P., Nilsson, N., & Raphael, B. (1968) · IEEE Transactions on Systems Science and Cybernetics · doi:10.1109/tssc.1968.300136 · Cited by 12,738 · see citing works
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302 · see citing works
Counterexample-Guided Abstraction Refinement
Clarke, E. M., Grümberg, O., Jha, S., et al. (2000) · Lecture notes in computer science · doi:10.1007/10722167_15 · Cited by 1,711 · see citing works
Combinatorial Optimization: Theory and Algorithms
Körte, B., & Vygen, J. (2012) · doi:10.1007/3-540-29297-7 · Cited by 1,156 · see citing works
Combinatorial optimization: Theory and algorithms
(2001) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(01)90023-9 · Cited by 604 · see citing works
Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy
Chakraborti, T., Sreedharan, S., Zhang, Y., & Kambhampati, S. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/23 · Cited by 359 · see citing works
Self-citationPlanning with Pattern Databases
Edelkamp, S. (2014) · Cited by 270 · see citing works
Explanation and abductive inference
Lombrozo, T. (2012) · The Oxford Handbook of Thinking and Reasoning · doi:10.1093/oxfordhb/9780199734689.013.0014 · Cited by 242 · see citing works
Planning in a hierarchy of abstraction spaces
Sacerdott, E. D. (1973) · Cited by 176 · see citing works
Explainable Agency for Intelligent Autonomous Systems
Langley, P., Meadows, B., Sridharan, M., & Choi, D. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i2.19108 · Cited by 156 · see citing works
Preferred Explanations: Theory and Generation via Planning
Sohrabi, S., Baier, J. A., & McIlraith, S. A. (2011) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v25i1.7845 · Cited by 102 · see citing works
Making Hybrid Plans More Clear to Human Users - A Formal Approach for Generating Sound Explanations
Seegebarth, B., Müller, F., Schattenberg, B., & Biundo, S. (2012) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v22i1.13503 · Cited by 77 · see citing works
Plan, Repair, Execute, Explain — How Planning Helps to Assemble your Home Theater
Bercher, P., Biundo, S., Geier, T., Hörnle, T., Nothdurft, F., Richter, F., & Schattenberg, B. (2014) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v24i1.13664 · Cited by 63 · see citing works
Angelic semantics for high-level actions
Marthi, B., Russell, S., & Wolfe, J. (2007) · Cited by 63 · see citing works
Counterexample-Guided Cartesian Abstraction Refinement
Seipp, J., & Helmert, M. (2013) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v23i1.13605 · Cited by 54 · see citing works
Incremental Lower Bounds for Additive Cost Planning Problems
Haslum, P. (2012) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v22i1.13511 · Cited by 49 · see citing works
Keyder, E., Hoffmann, J., & Haslum, P. (2012) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v22i1.13496 · Cited by 38 · see citing works
Diverse and Additive Cartesian Abstraction Heuristics
Seipp, J., & Helmert, M. (2014) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v24i1.13639 · Cited by 33 · see citing works
Young, N. E. (2008) · Encyclopedia of Algorithms · doi:10.1007/978-0-387-30162-4_175 · Cited by 30 · see citing works
Towards Clause-Learning State Space Search: Learning to Recognize Dead-Ends
Steinmetz, M., & Hoffmann, J. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10062 · Cited by 17 · see citing works
Bridging the gap between refinement and heuristics in abstraction
Bäckström, C., & Jönsson, P. (2013) · International Joint Conference on Artificial Intelligence · Cited by 16 · see citing works
Metaphysics of Planning Domain Descriptions
Srivastava, S., Russell, S., & Pinto, A. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10118 · Cited by 16 · see citing works
Self-citationA Classification of Plan Modification Strategies Based on Coverage and Information Requirements
Kambhampati, S. (1990) · Cited by 12 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 5
- Joseph C Culberson and Jonathan Schaeffer. Pattern databases. Computational In- telligence, 14(3):318-334, 1998.
- Maria Fox, Derek Long, and Daniele Mag- azzeni. Explainable Planning. In IJCAI XAI Workshop, 2017.
- Tania Lombrozo. The structure and func- tion of explanations. Trends in Cognitive Sciences, 10(10):464 -470, 2006.
- Tania Lombrozo. Explanation and abduc- tive inference. Oxford handbook of thinking and reason- ing, pages 260-276, 2012.
- Ben Leon Meadows, Pat Langley, and Miranda Jane Emery. Seeing beyond shadows: In- cremental abductive reasoning for plan understanding. In AAAI Workshop: Plan, Activity, and Intent Recognition, volume 13, page 13, 2013.
Cited by
Sorted by citations
Stepin, I., Alonso, J. M., Catala, A., & Pereira-Farina, M. (2021) · IEEE Access · doi:10.1109/access.2021.3051315 · Cited by 376 · see citing works
“analysis of counterfactual explanations in their ‘‘Hierarchical Expertise-Level Modeling’’ framework [156].”
BackgroundInfluentialContrastive explanation: a structural-model approach
Miller, T. (2021) · The Knowledge Engineering Review · doi:10.1017/s0269888921000102 · Cited by 186 · see citing works
- Authors
- Sreedharan, S., Srivastava, S., & Kambhampati, S.
- Affiliations
- Arizona State University (US)
- School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ 85281 USA
- Corresponding author
- Srivastava, Siddharth
- Venue
- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
- Published
- 2018-07
- Pages
- 4829-4836
- OpenAlex
- W2808460052
- Cited by
- 50
- References
- 23
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 4 · 2023: 3 · 2022: 6 · 2021: 10 · 2020: 17 · 2019: 4 · 2018: 1
- FWCI
- 3.27
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- Funders
- National Aeronautics and Space Administration (NNX17AD06G)
- Office of Naval Research (N00014-13-1-0176, N00014-15-1-2027, FA9550, N00014-13-1-0519, N00014)
- Air Force Office of Scientific Research (FA9550-, FA9550‐18‐1‐0067)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Keywords
- explainable AI, contrastive explanations, hierarchical models, NP-hardness, greedy approximation, autonomous systems, explanation generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
