The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
A brief Review on the Role of Context in Explainable AI
Abstract
While contextual data plays an important role for the outputs generated by AI models, it has not been fully considered when providing explanations about how and why those models generated such outputs. In the current paper we delve into previous research studies in order to provide an overview about the different uses of contextual data when enhancing the explanations for AI models. The inclusion and exclusion criteria are presented and a brief review of previous papers is captured, categorized by different ways to include contextual data into AI models. This paper pretends to foster research in leveraging the potential of contextual information for enhancing AI explainability.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
Explanations grounded in contextual information significantly improve understanding.
“explanations grounded in such contextual information significantly improve understanding [3, 7, 33].”
From "Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations (2026) · cites this paper as [3]
Citations
Cites
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762 · cited 1×
“For building trust in a AI-based system it is important that explanations take into consideration specific contexts, domain knowledge, and stakeholders’ and end-users’ interests [17].”
BackgroundSamek, W., Wiegand, T., & Müller, K.-R. (2017) · arXiv · doi:10.48550/arxiv.1708.08296 · Cited by 1,080
Ahmed, I., Jeon, G., & Piccialli, F. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3146552 · Cited by 853 · cited 1×
“Various other surveys on XAI are focused towards specific domains such as healthcare [23], industry [24], cyber-security [25], and finance [26].”
BackgroundWhat Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
Tonekaboni, S., Joshi, S., McCradden, M. D., & Goldenberg, A. (2019) · arXiv · doi:10.48550/arxiv.1905.05134 · Cited by 318
A Survey of Data-driven and Knowledge-aware eXplainable AI
Li, X.-H., Cao, C. C., Shi, Y., Bai, W., Gao, H., Qiu, L., Wang, C., Gao, Y., Zhang, S., Xue, X., et al. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2983930 · Cited by 224
Flagged first, then by citations
Research works printed but not linked: 36
- 10.1109/TNNLS.2020.3027314 · DOI · Paper page
- van Lent, An explainable artificial intelligence system for small-unit tactical behavior, 900
- 10.1609/aimag.v40i2.2850 · DOI · Paper page
- 10.1016/j.artint.2018.07.007 · DOI · Paper page
- 10.1109/DSAA.2018.00018 · DOI · Paper page
- 10.1145/3236009 · DOI · Paper page
- Biran, Explanation and justification in machine learning: A survey
- 10.1613/jair.1.13200 · DOI
- 10.1080/08839514.2018.1428490 · DOI
- 10.1007/3-540-48157-5_29 · DOI
- 10.1007/3-540-56602-3_158 · DOI
- 10.1016/j.eswa.2016.06.011 · DOI
- 10.1109/AERO55745.2023.10115751 · DOI
- 10.1016/j.artmed.2023.102498 · DOI
- 10.1007/s11023-019-09502-w · DOI
- 10.1007/s11948-020-00276-4 · DOI · Paper page
- 10.1109/access.2018.2870052 · DOI · Paper page
- 10.23919/MIPRO.2018.8400040 · DOI · Paper page
- 10.1109/TNNLS.2020.3027314 · DOI · Paper page
- 10.1109/ACCESS.2022.3204051 · DOI · Paper page
- 10.1109/ACCESS.2023.3347028 · DOI
- Doshi-Velez, 2017, Towards a rigorous science of interpretable machine learning, arXiv: 1702.08608 · arXiv
- 10.1007/978-3-030-30391-4_6 · DOI
- 10.14428/esann/2021.ES2021-124 · DOI
- Tekkesinoglu, 2021, Context-based image explanations for deep neural networks, Image and Vision Computing, 11, 104310
- 10.1007/978-3-030-82017-6_6 · DOI
- 10.3390/app131810068 · DOI
- 10.1016/j.asoc.2022.109854 · DOI
- 10.1007/s10844-020-00631-8 · DOI
- 10.32473/flairs.v35i.130646 · DOI
- 10.1145/3494322.3494359 · DOI
- 10.1109/ISMAR55827.2022.00067 · DOI
- Kim, Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV), 80, 2668
- 10.1016/j.inffus.2021.07.014 · DOI
- Al-Shedivat, 2020, Contextual explanation networks, Journal of Machine Learning Research, 21, 44
- 10.1109/icoiact55506.2022.9972118 · DOI
Cited by
Sorted by citations
Mathur, N., Rahman, H., & Desai, S. (2026) · Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772363.3798685 · Cited by 1
“…elements of their sociotechnical environments and their interaction history to interpret AI’s behavior, such as referencing physical objects, or prior conversations with the AI [23, 42, 53], and explanations grounded in such contextual information significantly improve understanding [3, 7, 33].”
Metadata
- Authors
- Baruah, R. D., & Organero, M. M.
- Affiliations
- Indian Institute of Technology Guwahati (IN)
- Carlos III University of Madrid,Department of Telematic Engineering,Leganés,Madrid,Spain
- ORCID
- Baruah, Rashmi Dutta
- Venue
- 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)
- Publisher
- IEEE
- Published
- 2024-05-23
- Pages
- 1-6
- OpenAlex
- W4400034227
- Cited by
- 2
- References
- 5
- Citations by year
- 2025: 2
- FWCI
- 0.59
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- explainable AI, contextual information, model explanation
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
