Accountability of AI Under the Law: The Role of Explanation
Open accessThe DOI matches its Crossref record; 24 of the 26 references it cites were found in a registry or an index; none of the 17 sources its claims cite is checked for support yet.
Abstract
The ubiquity of systems using artificial intelligence or "AI" has brought increasing attention to how those systems should be regulated. The choice of how to regulate AI systems will require care. AI systems have the potential to synthesize large amounts of data, allowing for greater levels of personalization and precision than ever before|applications range from clinical decision support to autonomous driving and predictive policing. That said, common sense reasoning [McCarthy, 1960] remains one of the holy grails of AI, and there exist legitimate concerns about the intentional and unintentional negative consequences of AI systems [Bostrom, 2003, Amodei et al., 2016, Sculley et al., 2014]. There are many ways to hold AI systems accountable. In this work, we focus on one: explanation. Questions about a legal right to explanation from AI systems was recently debated in the EU General Data Protection Regulation [Goodman and Flaxman, 2016, Wachter et al., 2017], and thus thinking carefully about when and how explanation from AI systems might improve accountability is timely. Good choices about when to demand explanation can help prevent negative consequences from AI systems, while poor choices may not only fail to hold AI systems accountable but also hamper the development of much-needed beneficial AI systems. Below, we briefly review current societal, moral, and legal norms around explanation, and then focus on the different contexts under which explanation is currently required under the law. We find that there exists great variation around when explanation is demanded, but there also exists important consistencies: when demanding explanation from humans, what we typically want to know is how and whether certain input factors affected the final decision or outcome. These consistencies allow us to list the technical considerations that must be considered if we desired AI systems that could provide kinds of explanations that are currently required of humans under the law. Contrary to popular wisdom of AI systems as indecipherable black boxes, we find that this level of explanation should often be technically feasible but may sometimes be practically onerous|there are certain aspects of explanation that may be simple for humans to provide but challenging for AI systems, and vice versa. As an interdisciplinary team of legal scholars, computer scientists, and cognitive scientists, we recommend that for the present, AI systems can and should be held to a similar standard of explanation as humans currently are; in the future we may wish to hold an AI to a different standard.
Overview
CoChat Summary
TL;DR
The paper argues that legally operative explanations from AI systems—human-interpretable information about factors and weights or counterfactual answers—are technically feasible and should initially be demanded of AI systems to the same extent as humans. It reviews legal contexts in the United States, United Kingdom, France, and Germany and proposes treating explanation systems as distinct from AI predictors.
Key findings
- The paper defines an explanation as human-interpretable information about the logic by which a decision-maker reached a conclusion, and says it should let an observer determine the extent to which a particular input was determinative or influential, via either important factors and their relative weight or answers to counterfactual questions.
- Society tends to demand explanations based on three factors: the impact of the decision, the possibility of contesting/correcting/compensating for error, and reason to believe an error has occurred or will occur; no single factor is dispositive.
- The legal survey finds variation: judges are generally required to give reasoned decisions in the UK, France, and Germany, while juries rarely explain; administrative agencies must explain decisions; the U.S. Fair Credit Reporting Act requires key negative credit factors; France’s Digital Republic Act creates a right to explanation for algorithmic public-sector decisions; GDPR Articles 13–15 and 22 address automated decision-making information and rights.
- Technically, local explanation and local counterfactual faithfulness can map to legally operative explanations without full transparency; an explanation system can be separate from the AI system and need not affect predictive accuracy, though concept-mapping and ex post term determination remain challenges; alternatives include empirical evidence and theoretical guarantees.
Methods
- Conceptual, legal, and technical analysis produced from over a dozen meetings of the Berkman Klein Center Working Group on AI Interpretability, a collaboration among legal scholars, computer scientists, and cognitive scientists.
- Comparative legal survey of explanation from two perspectives—the legal system as a decision-maker and as an enforcer of accountability—across the United States, United Kingdom, France, and Germany; the paper states the survey is far from comprehensive.
- No empirical dataset or quantitative experiment is reported; the analysis maps legal explanation requirements to AI technical concepts and offers recommendations.
Limitations
- The paper states there is little data to determine the actual costs of requiring AI systems to generate explanations, so the role of explanation must be re-evaluated as technology changes.
- The paper states technical challenges: mapping high-dimensional inputs to human-interpretable concepts, determining relevant terms ex post in litigation, and reverse-engineering risk from access to many explanations.
- Evident from the text: there is no empirical validation or cost measurement; the legal survey is explicitly not comprehensive; and the recommendations are normative and may not generalize across all AI contexts.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 15 Not valid · 15 Not checked · 138 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across both perspectives and countries, we find variations regarding the role of the explanation, who is obligated to provide it, and what type or amount of evidence is needed to trigger that obligation.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all of the jurisdictions we surveyed, adjudication of individual claims often requires one or both parties to generate explanations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Society is more likely explanation where the explanation can be acted on in some way.”
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By isolating the determinative factors of a decision, which can then be contested, counterfactual explanations promote accountability.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and access to an explanation might decrease observers' trust in some decisions.”
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
45 more claims
Create a free account to see all 168 claims and to verify the 17 references still open.
- Probably not a substantial claim. 107
- It may state two separate claims as one. 33
- The quote only partly states this claim. 1
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The use of “high dimensional” or “black box” prediction techniques typically favored in the machine learning community are generally problematic (since these approaches can predict race through other variables, whether or not race is explicitly encoded)—although methods that have been proposed to make these models more transparent have recently been adapted to address fairness46.”
From Predictably unequal: understanding and addressing concerns that algorithmic clinical prediction may increase health disparities (2020) · cites this paper as [46]
Experimental — accuracy not yet measured
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Telling more than we can know: Verbal reports on mental processes.
Nisbett, R. E., & Wilson, T. D. (1977) · Psychological Review · doi:10.1037/0033-295x.84.3.231 · Cited by 11,317
(2012) · Cited by 9,062
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909
Garg, A. X., Adhikari, N. K. J., McDonald, H., Rosas-Arellano, M. P., Devereaux, P. J., Beyene, J., Sam, J., & Haynes, R. B. (2005) · JAMA · doi:10.1001/jama.293.10.1223 · Cited by 2,936
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467
Concrete Problems in AI Safety
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016) · arXiv · doi:10.48550/arxiv.1606.06565 · Cited by 1,314
Wachter, S., Mittelstadt, B., & Floridi, L. (2017) · International Data Privacy Law · doi:10.1093/idpl/ipx005 · Cited by 1,308
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Rationalizing Neural Predictions
Lei, T., Barzilay, R., & Jaakkola, T. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1011 · Cited by 777
Research works printed but not linked: 1
- , 60 BUS. LAW. 737, 744 (2005).
Cited by
Items 201–300 of 443
Decision-making power and responsibility in an automated administration
Langer, C. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00152-1 · Cited by 29
A Decentralized Explanatory System for Intelligent Cyber-Physical Systems
Houzé, É., Dessalles, J.-L., Diaconescu, A., Menga, D., & Schumann, M. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82193-7_48 · Cited by 11
Generating User-friendly Explanations for Loan Denials using GANsPreprint
Srinivasan, R., Chander, A., & Pezeshkpour, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.10244 · Cited by 16
Toward Accountable and Explainable Artificial Intelligence Part One: Theory and Examples
Khan, M. M., & Vice, J. (2022) · IEEE Access · doi:10.1109/access.2022.3207812 · Cited by 17
Transparency and Fairness in Machine Learning Applications
Shook, J., Smith, R., & Antonio, A. (2018) · doi:10.37419/jpl.v4.i5.2 · Cited by 10
Alsalamah, S. A., Alsalamah, H. A., Alsalamah, H. A., Sheerah, H. A., Luther, K., & Lu, C. (2025) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-025-00537-x · Cited by 14
Salloum, S. A. (2024) · Studies in big data · doi:10.1007/978-3-031-52280-2_41 · Cited by 16
Recht im Sog der digitalen Transformation : Herausforderungen
Hoffmann‐Riem, W., & KG, M. S. G. &. C. (2023) · BiblioBoard Library Catalog (Open Research Library) · doi:10.1628/978-3-16-161200-8
Counterfactual Explanations for Arbitrary Regression ModelsPreprint
Spooner, T., Dervovic, D., Long, J., Shepard, J., Chen, J., & Magazzeni, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.15212 · Cited by 38
(2018) · doi:10.24963/ijcai.2018/10 · Cited by 10
Structural Logic of AI Surveillance and Its Normalisation in the Public Sphere
Park, Y. J. (2021) · Javnost - The Public · doi:10.1080/13183222.2021.1955323 · Cited by 16
Towards Balancing Preference and Performance through Adaptive Personalized Explainability
Silva, A., Tambwekar, P., Schrum, M., & Gombolay, M. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610977.3635000 · Cited by 24
Kim, S., Yi, S., & Park, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0326028 · Cited by 21
An Overview on the Explainability of Cyber-Physical Systems
Jha, S. S. (2022) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.v35i.130646 · Cited by 12
Teaching Meaningful ExplanationsPreprint
Codella, N., Hind, M., Ramamurthy, K. N., Campbell, M. S., Dhurandhar, A., Varshney, K. R., Wei, D., & Mojsilović, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11648 · Cited by 12
Unexplainability and Incomprehensibility of Artificial IntelligencePreprint
Yampolskiy, R. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03869 · Cited by 15
Juel, B. E., Comolatti, R., Tononi, G., & Albantakis, L. (2019) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00207.xml · Cited by 16
Explainable Legal Case Matching via Graph Optimal Transport
Sun, Z., Yu, W., Si, Z., Xu, J., Dong, Z., Chen, X., Xu, H., & Wen, J.-R. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3321935 · Cited by 16
Code-aware fault localization with pre-training and interpretable machine learning
Zhang, Z., Li, Y., Yang, S., Zhang, Z., & Lei, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121689 · Cited by 11
The Ethics of Artificial Intelligence in Legal Decision Making: An Empirical Study
DUTTA, B. M. (2023) · doi:10.48047/pne.2018.55.1.38 · Cited by 14
The data dance: choreographing seamless partnerships between humans, data, and GenAI
Durango, I., Gallud, J. A., & Penichet, V. M. R. (2024) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00684-w · Cited by 11
Obura, E. A., & Emoit, P. I. (2024) · Africa Education Review · doi:10.1080/18146627.2024.2440351 · Cited by 24
Kontiainen, L. E., Koulu, R., & Sankari, S. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.882134 · Cited by 20
Practical Machine Learning Safety: A Survey and PrimerPreprint
Mohseni, S., Wang, H., Yu, Z., Xiao, C., Wang, Z., & Yadawa, J. (2021) · arXiv (Cornell University) · Cited by 10
Beriaín, Í. D. M., & Estrada, M. J. P. (2020) · Revista de Derecho de la UNED (RDUNED) · doi:10.5944/rduned.25.2019.27013 · Cited by 8
Variable Importance Without Impossible Data
Mase, M., Owen, A. B., & Seiler, B. B. (2023) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-040722-045325 · Cited by 18
Identifying the 'Right' Level of Explanation in a Given SituationPreprint
Maxwell, W., Beaudouin, V., Bloch, I., Bounie, D., Clémençon, S., d’Alché–Buc, F., Eagan, J., Mozharovskyi, P., & Parekh, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3604924 · Cited by 13
Thoughts and Reflections on the Case of Qatar: Should Artificial Intelligence Be Regulated?
Badran, A. (2021) · Springer eBooks · doi:10.1007/978-981-16-0771-4_5 · Cited by 9
Right to an Explanation Considered HarmfulPreprint
Crabtree, A., Urquhart, L., & Chen, J. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3384790 · Cited by 8
Please Explain: Key Questions for Explainable AI research from an Organizational perspective
Hafermalz, E., & Huysman, M. (2021) · Morals & Machines · doi:10.5771/2747-5174-2021-2-10 · Cited by 17
Generative Neurosymbolic MachinesPreprint
Jiang, J., & Ahn, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12152 · Cited by 35
Automated Administrative Decision-Making: What is the Black Box Hiding?
Nešpor, J. (2024) · AUC IURIDICA · doi:10.14712/23366478.2024.23 · Cited by 5
Beyond Fairness Metrics: Roadblocks and Challenges for Ethical AI in PracticePreprint
Chen, J., Storchan, V., & Kurshan, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.06217 · Cited by 34
A guided tour of multiple criteria sorting models and methods
Belahcène, K., Mousseau, V., Ouerdane, W., Pirlot, M., & Sobrie, O. (2024) · Annals of Operations Research · doi:10.1007/s10479-024-06278-w · Cited by 12
Performance or Explainability? A Law of Armed Conflict Perspective
Kwik, J., & van Engers, T. (2023) · Law, governance and technology series · doi:10.1007/978-3-031-41081-9_14 · Cited by 7
Recommender Systems and Autonomy: A Role for Regulation of Design, Rights, and Transparency
Djeffal, C., Hitrova, C., & Magrani, E. (2021) · Indian Journal of Law and Technology · doi:10.55496/jgdn9214 · Cited by 10
Tzimas, T. (2021) · Law, governance and technology series · doi:10.1007/978-3-030-78585-7_4 · Cited by 9
Efficient Search for Diverse Coherent ExplanationsPreprint
Russell, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04909 · Cited by 27
Gadade, D. D., Kulkarni, D. A., Raj, R., Patil, S. G., & Modi, A. (2024) · Wiley eBooks · doi:10.1002/9781394234196.ch17 · Cited by 6
AI, IoT, and Blockchain: Business Models, Ethical Issues, and Legal Perspectives
Nehme, E., Salloum, H., Abdo, J. B., & Taylor, R. (2021) · Springer eBooks · doi:10.1007/978-3-030-74150-1_4 · Cited by 8
The Provision of Legal Services to Consumers Using LawTech Tools: From “Service” to “Legal Product”
Navarro, S. N. (2019) · Open Journal of Social Sciences · doi:10.4236/jss.2019.711007 · Cited by 6
Understanding Consumer Preferences for Explanations Generated by XAI AlgorithmsPreprint
Ramon, Y., Vermeire, T., Toubia, O., Martens, D., & Evgeniou, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.02624 · Cited by 25
Tiong, K. Y., Ma, Z., & Palmqvist, C.-W. (2025) · European Transport Research Review · doi:10.1186/s12544-024-00704-7 · Cited by 13
Niu, Y., Xie, H., Jia, H., Zhao, L., Liu, L., Liu, P., Li, X., Wang, R., & Li, Y. (2025) · Cancer Medicine · doi:10.1002/cam4.71077 · Cited by 8
AI Hallucination and Strategies to Overcome: Enhancing Human-AI Interaction
Kushwah, S., & Dave, N. (2025) · International Conference on Artificial Intelligence and Machine Vision (AIMV) · doi:10.1109/aimv66517.2025.11203756 · Cited by 7
Looking Inside the Black Box: Core Semantics Towards Accountability of Artificial Intelligence
Garigliano, R., & Mich, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30985-5_16 · Cited by 7
Unmasking the Shadows: Exploring Unethical AI Implementation
Dwivedi, D. N., & Mahanty, G. (2024) · Advances in human resources management and organizational development book series · doi:10.4018/979-8-3693-0724-3.ch012 · Cited by 7
Moral Issues in the Natural Sciences and Technologies
van den Heever, J., & Jones, C. (2019) · doi:10.4102/aosis.2019.bk114 · Cited by 9
Cooman, J. D. (2023) · Journal of European Competition Law & Practice · doi:10.1093/jeclap/lpad017 · Cited by 10
Flexible and Context-Specific AI Explainability: A Multidisciplinary ApproachPreprint
Beaudouin, V., Bloch, I., Bounie, D., Clémençon, S., d’Alché–Buc, F., Eagan, J., Maxwell, W., Mozharovskyi, P., & Parekh, J. (2020) · arXiv (Cornell University) · Cited by 21
Künstliche Intelligenz/Maschinelles Lernen
(2021) · doi:10.1007/978-3-476-04901-8_81 · Cited by 5
Perspectives de l'emploi de l'OCDE
OECD (2009) · Perspectives de l'emploi de l'OCDE/OCDE perspectives de l'emploi · doi:10.1787/19991274 · Cited by 5
An Introduction to the Principle of Transparency in Automated Decision-Making Systems
Rendón, L. G. (2022) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro55190.2022.9803417 · Cited by 12
Winslow, B. D., Garibay, Ö. Ö., Goyal, T., Koon, S., Margetis, G., Salvendy, G., Shneiderman, B., Tayebi, A., & Vardoulakis, L. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2641703 · Cited by 16
Investigating Car Drivers’ Information Demand after Safety and Security Critical Incidents
Gröber, L. T., Fassl, M., Gupta, A., & Krombholz, K. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3446862 · Cited by 5
Subjectivity of Explainable Artificial Intelligence
Raikov, A. (2022) · Russian Journal of Philosophical Sciences · doi:10.30727/0235-1188-2022-65-1-72-90 · Cited by 7
Explainable Artificial Intelligence (XAI): A reason to believe?
Adamson, G. (2022) · Law in context · doi:10.26826/law-in-context.v37i3.177 · Cited by 12
Exploring Clusters of Research in Three Areas of AI Safety
(2022) · doi:10.51593/20210026 · Cited by 5
Natural Language Processing for HR Chatbots and Virtual Assistants
Singh, A. K., Lakhera, G., Ojha, M., Mishra, A. K., & Kaushik, S. (2024) · Advances in logistics, operations, and management science book series · doi:10.4018/979-8-3693-3318-1.ch020 · Cited by 6
Big Data in Gesundheitswesen und Medizin
Rüping, S., & Sander, J. (2018) · Springer eBooks · doi:10.1007/978-3-662-57611-3_2 · Cited by 10
Defining the Collective Intelligence Supply Chain
Barclay, I., Preece, A. D., & Taylor, I. (2018) · ORCA Online Research @Cardiff (Cardiff University) · doi:10.48550/arxiv.1809.09444 · Cited by 8
Mishra, A., Savulescu, J., & Giubilini, A. (2022) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780198857815.013.25 · Cited by 6
XAI-Eval: A framework for comparative evaluation of explanation methods in healthcare
Agrawal, K., Shawi, R. E., & Ahmed, N. M. O. S. (2025) · Digital Health · doi:10.1177/20552076251368045 · Cited by 11
Fuzzy Rules for Explaining Deep Neural Network Decisions (FuzRED)
Buczak, A. L., Baugher, B. D., & Zaback, K. (2025) · Electronics · doi:10.3390/electronics14101965 · Cited by 8
Scherer, L., Kuss, M., & Nahm, W. (2023) · Advances in Kidney Disease and Health · doi:10.1053/j.akdh.2022.11.002 · Cited by 6
Ethical and Legal Challenges of Digital Medicine in Pandemics
Minssen, T., & Gerke, S. (2023) · Springer eBooks · doi:10.1007/978-3-662-66872-6_12 · Cited by 5
Lawson, C. G. R., Englezos, E., & Rourke, M. F. (2025) · Plants People Planet · doi:10.1002/ppp3.70007 · Cited by 9
More Persuasive Explanation Method for End-to-End Driving Models
Zhang, C., Deguchi, D., Okafuji, Y., & Murase, H. (2023) · IEEE Access · doi:10.1109/access.2023.3235739 · Cited by 5
EMIL: Extracting Meaning from Inconsistent Language
Straß, H., Wyner, A., & Diller, M. (2019) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2019.04.010 · Cited by 4
Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth
Davoudi, S. P. M., Davodi, A. G., Amiri-Margavi, A., & Jafari, M. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391148 · Cited by 16
Borba, R. L., Ferreira, I. E. D. P., & Ramos, P. H. B. (2024) · Technovation · doi:10.1016/j.technovation.2024.103118 · Cited by 7
Co-creation in Transhuman Realities: Setting the Stage for Transformative Learning
Stary, C. (2020) · Cognitive technologies · doi:10.1007/978-3-030-56546-6_15 · Cited by 5
Objective-Based Counterfactual Explanations for Linear Discrete Optimization
Korikov, A., & Beck, J. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-33271-5_2 · Cited by 6
Trustworthy AI in Heterogeneous Settings: Federated Learning of Explainable Classifiers
Daole, M., Ducange, P., Marcelloni, F., & Renda, A. (2024) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee60900.2024.10612109 · Cited by 9
A Process-Oriented Framework for Regulating Artificial Intelligence Systems
Stranieri, A., & Sun, Z. (2022) · Advances in business information systems and analytics book series · doi:10.4018/978-1-7998-9016-4.ch005 · Cited by 9
Bioethics Legal Implications of Artificial Intelligence in Medicine
Joshi, N. V., Selvakumar, P., Srivastava, N., Manjeet, Das, A., & Manjunath, T. C. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5646-4.ch002 · Cited by 4
Efficient computation of contrastive explanations
Artelt, A., & Hammer, B. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534454 · Cited by 11
Bilimsel Araştırmalarda Yapay Zekâ Kullanımı Etik İlkeleri
Alakuş, H., & Yılmaz, K. (2025) · MANAS Sosyal Araştırmalar Dergisi · doi:10.33206/mjss.1663647 · Cited by 5
Evidence-based explanation to promote fairness in AI systemsPreprint
Ferreira, J. J., & Monteiro, M. D. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01525 · Cited by 9
Due Process, Fair Trial, Transparency, and Explainability
Ebers, M., & Trasberg, H. (2023) · Data science, machine intelligence, and law · doi:10.1007/978-3-031-19667-6_6 · Cited by 3
Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models
Amiri-Margavi, A., Jebellat, I., Jebellat, E., & Davoudi, S. P. M. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-96235-6_22 · Cited by 10
Casimiro, J. S. C., & Teixeira, S. T. (2024) · Beijing Law Review · doi:10.4236/blr.2024.152044 · Cited by 6
Value-Based Core Areas of Trustworthiness in Online Services
Guamán, D. S., Álamo, J. M. D., Veljanova, H., Reichmann, S., & Haselbacher, A. (2019) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-33716-2_7 · Cited by 4
Trustworthy Machine Learning for Cloud-Based Internet of Things (IoT)
Yadav, S., Joshi, R. C., & Yadav, D. (2022) · Springer eBooks · doi:10.1007/978-3-030-86749-2_9 · Cited by 5
Stranieri, A., & Sun, Z. (2021) · Advances in data mining and database management book series · doi:10.4018/978-1-7998-4963-6.ch003 · Cited by 3
Autissier, D., Guillard, A., & Goff, P. L. (2024) · Question(s) de management · doi:10.3917/qdm.230.0123 · Cited by 3
HEX: Human-in-the-loop explainability via deep reinforcement learning
Lash, M. T. (2024) · Decision Support Systems · doi:10.1016/j.dss.2024.114304 · Cited by 11
Crisan, A., Butters, N., & Zoe (2024) · IEEE Evaluation and Beyond - Methodological Approaches for Visualization (BELIV) · doi:10.1109/beliv64461.2024.00007 · Cited by 6
Algorithmic Decision Making in Education: Challenges and Opportunities
Levantis, N., & Sgora, A. (2024) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon60312.2024.10578645 · Cited by 11
In Defense of Sociotechnical Pragmatism
Watson, D., & Mökander, J. (2023) · Digital ethics lab yearbook · doi:10.1007/978-3-031-28678-0_10 · Cited by 4
Arsić, S., Mihic, M. M., Petrović, D. Č., Mitrović, Z., Kostić, S. C., & Mihić, O. R. (2024) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa59508.2024.10467907 · Cited by 4
Explanatory Pluralism in Explainable AI
Yao, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-84060-0_18 · Cited by 10
Prediction of Fetal Blood Pressure during Labour with Deep Learning Techniques
Tolladay, J., Lear, C. A., Bennet, L., Gunn, A. J., & Georgieva, A. (2023) · Bioengineering · doi:10.3390/bioengineering10070775 · Cited by 3
Do Charge Prediction Models Learn Legal Theory?
An, Z., Huang, Q., Jiang, C., Feng, Y., & Zhao, D. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.275 · Cited by 14
Using Issues to Explain Legal DecisionsPreprint
Bench-Capon, T. J. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14688 · Cited by 6
A Pragmatic Regulatory Framework for Artificial Intelligence
Karisma, K. (2021) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-7927-5.ch002 · Cited by 3
Wenn Algorithmen für uns entscheiden: Chancen und Risiken der künstlichen Intelligenz
Christen, M., Mader, C., Čas, J., Abou‐Chadi, T., Bernstein, A., Binder, N. B., Dell’Aglio, D., Fabbian, L., George, D., Gohdes, A., et al. (2020) · vdf Hochschulverlag AG an der ETH Zürich eBooks · doi:10.1553/10.3218/4002-9 · Cited by 21
On the Path to the Future: Mapping the Notion of Transparency in the EU Regulatory Framework for AIPreprint
Varošanec, I. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4066020 · Cited by 3
Explaining Natural Language Processing Classifiers with Occlusion and Language ModelingPreprint
Harbecke, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.11889 · Cited by 6
On Controllability in Agentic AI: A Survey
Nguyen, M. H., Nguyen, D.-H., O’Sullivan, B., & Nguyen, H. D. (2026) · Minds and Machines · doi:10.1007/s11023-026-09783-y · Cited by 10
Metadata
- Authors
- Doshi-Velez, F., Kortz, M., Budish, R., Bavitz, C., Gershman, S. J., O'Brien, D., Scott, K., Shieber, S., Waldo, J., Weinberger, D., Weller, A., & Wood, A.
- Affiliations
- Harvard University (US)
- University of Manchester (GB)
- University of Cambridge (GB)
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2017
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W2765811634
- Cited by
- 457
- References
- 26
- Citations by year
- 2026: 36 · 2025: 56 · 2024: 64 · 2023: 49 · 2022: 58 · 2021: 64 · 2020: 55 · 2019: 51 · 2018: 21 · 2017: 1
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- Digital Access to Scholarship at Harvard (DASH) (Harvard University) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Law › Digitalization, Law, and Regulation
- Keywords
- AI accountability, legal explanation, right to explanation, AI regulation, General Data Protection Regulation, explainable AI, black box problem, human-AI comparison, AI decision transparency
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.
A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.