Explainable Generative AI (GenXAI): a survey, conceptualization, and research agenda
Open accessThe DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.
Abstract
Generative AI (GenAI) represents a shift from AI’s ability to “recognize” to its ability to “generate” solutions for a wide range of tasks. As generated solutions and applications grow more complex and multi-faceted, new needs, objectives, and possibilities for explainability (XAI) have emerged. This work elaborates on why XAI has gained importance with the rise of GenAI and the challenges it poses for explainability research. We also highlight new and emerging criteria that explanations should meet, such as verifiability, interactivity, security, and cost considerations. To achieve this, we focus on surveying existing literature. Additionally, we provide a taxonomy of relevant dimensions to better characterize existing XAI mechanisms and methods for GenAI. We explore various approaches to ensure XAI, ranging from training data to prompting. Our paper provides a concise technical background of GenAI for non-technical readers, focusing on text and images to help them understand new or adapted XAI techniques for GenAI. However, due to the extensive body of work on GenAI, we chose not to delve into detailed aspects of XAI related to the evaluation and usage of explanations. Consequently, the manuscript appeals to both technical experts and professionals from other fields, such as social scientists and information systems researchers. Our research roadmap outlines over ten directions for future investigation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00371 · Cited by 11,953
Analyzing the Past to Prepare for the Future: Writing a Literature Review
Webster, J., & Watson, R. T. (2002) · MIS Quarterly · doi:10.2307/4132319 · Cited by 7,449
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Explanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
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
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 1×
“It can also encode additional domain-specific knowledge, such as medical information (Singhal et al. 2023).”
Large language models in medicine
Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023) · Nature Medicine · doi:10.1038/s41591-023-02448-8 · Cited by 3,944
BAİDOO-ANU, D., & OWUSU ANSAH, L. (2023) · Journal of AI · doi:10.61969/jai.1337500 · Cited by 3,939
Baidoo-Anu, D., & Owusu Ansah, L. (2023) · doi:10.2139/ssrn.4337484 · Cited by 3,004
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Guidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439 · cited 1×
“For example, guidelines for human-AI interaction (before GenAI) are well-studied (Amershi et al. 2019), as is the topic of explanation in collaborative human-AI systems (Theis et al. 2023).”
Diffusion Models: A Comprehensive Survey of Methods and Applications
Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., & Yang, M.-H. (2024) · ACM Computing Surveys · doi:10.1145/3626235 · Cited by 1,704 · cited 5×
“Many works have surveyed various aspects of GenAI (excluding XAI) (Xu et al. 2023; Lin et al. 2022; Xing et al. 2023; Yang et al. 2023b; Zhang et al. 2023a, c; Pan et al. 2023).”
InfluentialLin, T., Wang, Y., Liu, X., & Qiu, X. (2022) · AI Open · doi:10.1016/j.aiopen.2022.10.001 · Cited by 1,422
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2021) · arXiv · doi:10.48550/arxiv.2106.04554 · Cited by 1,420
Explainable AI (XAI): Core Ideas, Techniques, and Solutions
Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., Qian, B., Wen, Z., Shah, T., Morgan, G., et al. (2023) · ACM Computing Surveys · doi:10.1145/3561048 · Cited by 1,386
Sanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B., & Yang, Q. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581388 · Cited by 1,274
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · arXiv · doi:10.48550/arxiv.2005.00661 · Cited by 1,185 · cited 1×
“However, the issue that outputs of LLMs cannot be verified (due to hallucinations) was discussed years earlier (Maynez et al. 2020).”
A method for taxonomy development and its application in information systems
Nickerson, R. C., Varshney, U., & Muntermann, J. (2013) · European Journal of Information Systems · doi:10.1057/ejis.2012.26 · Cited by 1,143 · cited 2×
“To this end, we opted for a narrative review methodology (King and He 2005) combined with a taxonomy development approach from the field of information systems (Nickerson et al. 2013).”
Multimodal learning with transformers: A survey
Xu, P., Zhu, X., & Clifton, D. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275156 · Cited by 1,072
Explainable artificial intelligence: a comprehensive review
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10088-y · Cited by 983
Can Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2023) · arXiv · doi:10.48550/arxiv.2305.03514 · Cited by 839
Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
Saeed, W., & Omlin, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110273 · Cited by 783
Interpretation of Neural Networks Is Fragile
Ghorbani, A., Abid, A., & Zou, J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013681 · Cited by 765
Taxonomy of Risks posed by Language Models
Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P.-S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533088 · Cited by 764 · cited 3×
“Alignment Tuning LLMs might not incorporate human values and preferences, producing harmful, misleading, and biased outputs (Shen et al. 2023; Weidinger et al. 2022).”
Serrano, S., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1282 · Cited by 690
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
A Multiscale Visualization of Attention in the Transformer Model
Vig, J. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3007 · Cited by 600
Can Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2024) · Computational Linguistics · doi:10.1162/coli_a_00502 · Cited by 585
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Ross, A. S., Hughes, M. C., & Doshi-Velez, F. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/371 · Cited by 515 · cited 2×
“Common strategies involve disentangling latent dimensions (Ross et al. 2017) and training for XAI-relevant criteria, such as citing evidence (Menick et al. 2022).”
Katz, D. M., Bommarito, M. J., Gao, S., & Arredondo, P. (2024) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2023.0254 · Cited by 420 · cited 1×
“GenAI has shown unprecedented capabilities like passing university-level exams (Choi et al. 2021; Katz et al. 2024).”
Shahsavar, Y., & Choudhury, A. (2023) · JMIR Human Factors · doi:10.2196/47564 · Cited by 341 · cited 2×
“Users might seek advice for pressing personal problems (Shahsavar and Choudhury 2023) or use GenAI for educational purposes.”
Targeted Syntactic Evaluation of Language Models
Marvin, R., & Linzen, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1151 · Cited by 334
ChatGPT outperforms humans in emotional awareness evaluations
Elyoseph, Z., Hadar-Shoval, D., Asraf, K., & Lvovsky, M. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1199058 · Cited by 324 · cited 1×
“Unknown Applications Since generative AI can process any text, image, or other medium as input and output, it is difficult to anticipate all possible applications.”
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Georgiev, P., Lei, V. I., Burnell, R., Bai, L., Gulati, A., Tanzer, G., Vincent, D., Pan, Z., Wang, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.05530 · Cited by 306
Zoom In: An Introduction to Circuits
Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., & Carter, S. (2020) · Distill · doi:10.23915/distill.00024.001 · Cited by 288 · cited 1×
“These functions are based on the idea that there are more features than neurons per layer, and, in turn, superposition yields additional features (Olah et al. 2020).”
Factual Probing Is [MASK]: Learning vs. Learning to Recall
Zhong, Z., Friedman, D., & Chen, D. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.398 · Cited by 274
ChatGPT is not all you need. A state-of-the-art review of large generative AI models
Gozalo-Brizuela, R., & Garrido-Merchan, E. C. (2023) · arXiv · doi:10.48550/arxiv.2301.04655 · Cited by 245
Large Language Models Can Self-Improve
Huang, J., Gu, S. S., Hou, L., Wu, Y., Wang, X., Yu, H., & Han, J. (2022) · arXiv · doi:10.48550/arxiv.2210.11610 · Cited by 230
Large Language Models Can Self-Improve
Huang, J., Gu, S., Hou, L., Wu, Y., Wang, X., Yu, H., & Han, J. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.67 · Cited by 230
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Wortman Vaughan, J. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.8036d03b · Cited by 210
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Vaughan, J. W. (2023) · arXiv · doi:10.48550/arxiv.2306.01941 · Cited by 209 · cited 1×
“Many of our novel aspects, in particular, cannot be found in prior works.”
Schramowski, P., Stammer, W., Teso, S., Brugger, A., Herbert, F., Shao, X., Luigs, H.-G., Mahlein, A.-K., & Kersting, K. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0212-3 · Cited by 207
Knowledge Neurons in Pretrained Transformers
Dai, D., Dong, L., Hao, Y., Sui, Z., Chang, B., & Wei, F. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.581 · Cited by 187
Position Information in Transformers: An Overview
Dufter, P., Schmitt, M., & Schütze, H. (2022) · Computational Linguistics · doi:10.1162/coli_a_00445 · Cited by 175 · cited 1×
“3) has many variations (Lin et al. 2022), mostly involving different implementations of individual elements, such as different types of positional embeddings (Dufter et al. 2022), different types of attention (de San-tana Correia and Colombini 2022), or even replacing some components.”
Personalized Prompt Learning for Explainable Recommendation
Li, L., Zhang, Y., & Chen, L. (2023) · ACM Transactions on Information Systems · doi:10.1145/3580488 · Cited by 172 · cited 1×
“Some sub-areas of GenAI, such as knowledge identification and editing (Zhang et al. 2024), use isolated XAI techniques as tools but do not aim to elaborate on them generally.”
Towards Interpretable Mental Health Analysis with Large Language Models
Yang, K., Ji, S., Zhang, T., Xie, Q., Kuang, Z., & Ananiadou, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.370 · Cited by 155 · cited 5×
“Many works have surveyed various aspects of GenAI (excluding XAI) (Xu et al. 2023; Lin et al. 2022; Xing et al. 2023; Yang et al. 2023b; Zhang et al. 2023a, c; Pan et al. 2023).”
InfluentialExplaining machine learning models with interactive natural language conversations using TalkToModel
Slack, D., Krishna, S., Lakkaraju, H., & Singh, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00692-8 · Cited by 125
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Geva, M., Caciularu, A., Wang, K. R., & Goldberg, Y. (2022) · arXiv · doi:10.48550/arxiv.2203.14680 · Cited by 123
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Räuker, T., Ho, A., Casper, S., & Hadfield-Menell, D. (2023) · 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml54575.2023.00039 · Cited by 122
Silva, A., Schrum, M., Hedlund-Botti, E., Gopalan, N., & Gombolay, M. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2101698 · Cited by 104
Hyena Hierarchy: Towards Larger Convolutional Language Models
Poli, M., Massaroli, S., Nguyen, E., Fu, D. Y., Dao, T., Baccus, S., Bengio, Y., Ermon, S., & Ré, C. (2023) · arXiv · doi:10.48550/arxiv.2302.10866 · Cited by 96 · cited 1×
“2022 ) T e x t t o 3 D I npu t: T e x t d e s c r i b i ng ob j ec t O u t pu t: 3 D r e p r e s e n t a ti on o f ob j ec t .”
Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., & Wang, W. Y. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00660 · Cited by 86
Fok, R., & Weld, D. S. (2024) · AI Magazine · doi:10.1002/aaai.12182 · Cited by 81
Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
Gao, Y., Sheng, T., Xiang, Y., Xiong, Y., Wang, H., & Zhang, J. (2023) · arXiv · doi:10.48550/arxiv.2303.14524 · Cited by 79
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
Ye, X., & Durrett, G. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2202 · Cited by 75
Reed, S., Zolna, K., Parisotto, E., Colmenarejo, S. G., Novikov, A., Barth-Maron, G., Gimenez, M., Sulsky, Y., Kay, J., Springenberg, J. T., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.06175 · Cited by 63
Flexible and Context-Specific AI Explainability: A Multidisciplinary Approach
Beaudouin, V., Bloch, I., Bounie, D., Clémençon, S., d'Alché-Buc, F., Eagan, J., Maxwell, W., Mozharovskyi, P., & Parekh, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3559477 · Cited by 61
Fok, R., & Weld, D. S. (2023) · arXiv · doi:10.48550/arxiv.2305.07722 · Cited by 54
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Wang, K., Variengien, A., Conmy, A., Shlegeris, B., & Steinhardt, J. (2022) · arXiv · doi:10.48550/arxiv.2211.00593 · Cited by 52
Rethinking with Retrieval: Faithful Large Language Model Inference
He, H., Zhang, H., & Roth, D. (2023) · arXiv · doi:10.48550/arxiv.2301.00303 · Cited by 50
Faithful Reasoning Using Large Language Models
Creswell, A., & Shanahan, M. (2022) · arXiv · doi:10.48550/arxiv.2208.14271 · Cited by 37
Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., & Wang, W. Y. (2023) · arXiv · doi:10.48550/arxiv.2308.03188 · Cited by 25
Cited by
Retrieval-Augmented Generation (RAG)
Klesel, M., & Wittmann, H. F. (2025) · Business & Information Systems Engineering · doi:10.1007/s12599-025-00945-3 · Cited by 92
“We argue that the impact of grounding is still under-researched, and more empirical data is required to investigate if grounding is a valuable addition to XAI.”
AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents
Karim, M. M., Van, D. H., Khan, S., Qu, Q., & Kholodov, Y. (2025) · Future Internet · doi:10.3390/fi17020057 · Cited by 73
Establishing and evaluating trustworthy AI: overview and research challenges
Kowald, D., Scher, S., Pammer-Schindler, V., Müllner, P., Waxnegger, K., Demelius, L., Fessl, A., Toller, M., Mendoza Estrada, I. G., Šimić, I., et al. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1467222 · Cited by 59
Patel, K., Shah, M., Qureshi, K. M., & Qureshi, M. R. N. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11435-z · Cited by 42
Sustainable AI: Emerging Trends, Impacts, and Future Challenges
Philipo, A. G., Ning, H., Sarwatt, D. S., Mohamed, J. A., Yusufu, A. S., Shi, F., Urenje, S., & Ding, J. (2025) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2025.3611272 · Cited by 9
“Balancing openness with legal, ethical, and privacy requirements is vital for responsible AI adoption [125], [126].”
Metadata
- Authors
- Schneider, J.
- Venue
- Artificial Intelligence Review
- Published
- 2024-09-15
- Volume
- 57
- Issue
- 11
- ISSN
- 0269-2821 (ISSN-L)
- 1573-7462
- OpenAlex
- W4402553424
- Cited by
- 156
- References
- 67
- FWCI
- 23.22
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.