Contrastive Constraints Guide Explanation‐Based Category Learning
Abstract
This paper provides evidence for a contrastive account of explanation that is motivated by pragmatic theories that recognize the contribution that context makes to the interpretation of a prompt for explanation. This study replicates the primary findings of previous work in explanation‐based category learning (Williams & Lombrozo, 2010), extending that work by illustrating the critical role of the context in this type of learning. Participants interacted with items from two categories either by describing the items or explaining their category membership. We manipulated the feature overlap between the categories and examined both the explanations generated and acquired knowledge of the categories. Explanations for membership in a given category were influenced by the unprompted contrast category, indicating an important role for contrastive processing in the generation of explanations. The influence of the contrast category was similarly seen in the transfer performance of the participants.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Fernández et al. introduce the notion of counterfactual sets to enhance counterfactual diversity.
“Fernández et al. introduce the notion of counterfactual sets to enhance counterfactual diversity [81].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [81]
Fernández et al. explain random forest predictions by fusing different tree predictors so that the resulting counterfactual set contains the most relevant counterfactual.
“They explain random forest predictions by fusing different tree predictors so that the resulting counterfactual set contains the most relevant counterfactual.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [81]
The other neighboring counterfactuals serve to diversify the output explanation.
“The other neighboring counterfactuals serve to diversify the output explanation.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [81]
The most commonly acceptable definition of a counterfactual in the observed RQ3-related studies states that a counterfactual explanation is a set of minimal feature modifications that makes the model change the prediction.
“Nevertheless, the most commonly acceptable definition of a contfactual in the observed RQ 3 -related studies states that a contfactual explanation is a set of minimal feature modifications that makes the model change the prediction [81], [105], [122].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [81]
Cites
Tversky, A. (1977) · Psychological Review · doi:10.1037/0033-295x.84.4.327 · Cited by 7,414 · see citing works
Fraassen, B. C. V. (1980) · doi:10.1093/0198244274.001.0001 · Cited by 4,682 · see citing works
Advances in Instructional Psychology
(2019) · Routledge eBooks · doi:10.4324/9781315864341 · Cited by 2,538 · see citing works
Eliciting Self‐Explanations Improves Understanding
Chi, M. T. H., Leeuw, N. D., Chiu, M., & Lavancher, C. (1994) · Cognitive Science · doi:10.1016/0364-0213(94)90016-7 · Cited by 2,406 · see citing works
Proceedings of the 29th Annual Conference of the Cognitive Science Society
Rohde, H., Kehler, A., & Elman, J. L. (2007) · Cognitive Science · Cited by 1,782 · see citing works
Eliciting Self‐Explanations Improves Understanding
Chi, M. T. H., De Leeuw, N., Chiu, M., & Lavancher, C. (1994) · Cognitive Science · doi:10.1207/s15516709cog1803_3 · Cited by 757 · see citing works
The structure and function of explanations.
Lombrozo, T. (2006) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2006.08.004 · Cited by 729 · see citing works
Conversational processes and causal explanation.
Hilton, D. J. (1990) · Psychological Bulletin · doi:10.1037/0033-2909.107.1.65 · Cited by 456 · see citing works
Schaffer, J. (2005) · The Philosophical Review · doi:10.1215/00318108-114-3-327 · Cited by 393 · see citing works
Functional explanation and the function of explanation
Lombrozo, T., & Carey, S. E. (2005) · Cognition · doi:10.1016/j.cognition.2004.12.009 · Cited by 301 · see citing works
On the Interaction of Theory and Data in Concept Learning
Wisniewski, E. J., & Medin, D. L. (1994) · Cognitive Science · doi:10.1016/0364-0213(94)90002-7 · Cited by 279 · see citing works
The Situated Nature of Concepts
Yeh, W., & Barsalou, L. W. (2006) · The American Journal of Psychology · doi:10.2307/20445349 · Cited by 278 · see citing works
The Role of Explanation in Discovery and Generalization: Evidence From Category Learning
Williams, J. J., & Lombrozo, T. (2010) · Cognitive Science · doi:10.1111/j.1551-6709.2010.01113.x · Cited by 190 · see citing works
On the Interaction of Theory and Data in Concept Learning
Wisniewski, E. J., & Medin, D. L. (1994) · Cognitive Science · doi:10.1207/s15516709cog1802_2 · Cited by 170 · see citing works
Goldstone, R. L., Medin, D. L., & Halberstadt, J. B. (1997) · Memory & Cognition · doi:10.3758/bf03201115 · Cited by 127 · see citing works
The Instrumental Value of Explanations
Lombrozo, T. (2011) · Philosophy Compass · doi:10.1111/j.1747-9991.2011.00413.x · Cited by 118 · see citing works
Explanation and prior knowledge interact to guide learning
Williams, J. J., & Lombrozo, T. (2012) · Cognitive Psychology · doi:10.1016/j.cogpsych.2012.09.002 · Cited by 105 · see citing works
Explanation and categorization: How “why?” informs “what?”
Lombrozo, T. (2008) · Cognition · doi:10.1016/j.cognition.2008.10.007 · Cited by 94 · see citing works
Causation and contrast classes
Northcott, R. (2007) · Philosophical Studies · doi:10.1007/s11098-007-9105-0 · Cited by 85 · see citing works
Chin‐Parker, S., & Ross, B. H. (2004) · Journal of Experimental Psychology Learning Memory and Cognition · doi:10.1037/0278-7393.30.1.216 · Cited by 80 · see citing works
Self-citationSinnott-Armstrong, W. P. (2008) · Social Epistemology · doi:10.1080/02691720802546120 · Cited by 67 · see citing works
Oaksford, M. (2002) · Thinking & Reasoning · doi:10.1080/13546780143000170 · Cited by 63 · see citing works
Environment and Goals Jointly Direct Category Acquisition
Love, B. C. (2005) · Current Directions in Psychological Science · doi:10.1111/j.0963-7214.2005.00363.x · Cited by 29 · see citing works
Chin‐Parker, S., & Bradner, A. (2009) · Cognitive Processing · doi:10.1007/s10339-009-0341-4 · Cited by 24 · see citing works
Self-citationGale, M. B., & Ball, L. J. (2011) · Memory & Cognition · doi:10.3758/s13421-011-0159-z · Cited by 18 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
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
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
“Chin-Parker and Bradner [17] as well as Chin-Parker and Cantelon [76] provide a unified theoretical framework for causal and non-causal contrastive explanation for category learning.”
BackgroundContrastive explanation: a structural-model approach
Miller, T. (2021) · The Knowledge Engineering Review · doi:10.1017/s0269888921000102 · Cited by 186 · see citing works
A contrastive account of explanation generation
Chin-Parker, S., & Bradner, A. (2017) · Psychonomic Bulletin & Review · doi:10.3758/s13423-017-1349-x · Cited by 15 · see citing works
Self-citation
- Authors
- Chin‐Parker, S., & Cantelon, J.
- Affiliations
- Denison University (US)
- Tufts University (US)
- Corresponding author
- Chin‐Parker, Seth
- ORCID
- Cantelon, Julie
- Venue
- Cognitive Science
- Publisher
- Wiley
- Published
- 2016-08-26
- Volume
- 41
- Issue
- 6
- Pages
- 1645-1655
- ISSN
- 0364-0213 (ISSN-L)
- 1551-6709
- OpenAlex
- W2512823917
- Cited by
- 18
- References
- 25
- Citations by year
- 2024: 2 · 2022: 1 · 2021: 7 · 2020: 3 · 2019: 2 · 2018: 1 · 2017: 2
- FWCI
- 2.37
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Cognitive Science (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
- Social Sciences › Psychology › Developmental and Educational Psychology › Child and Animal Learning Development
- Keywords
- context effects, explanation generation, feature overlap, transfer performance, category membership
- MeSH terms
- Concept Formation, Generalization, Psychological, Humans, Learning, Neuropsychological Tests, Transfer, Psychology, Knowledge
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
