Journal of AI-Driven Communication Engineering

Special Issue: Artificial Intelligence Across the Communication Stack: Engineering, Human Interaction, and Governance in the 6G Era

Vol. 2 (2026)

Human–Machine Communication in the Age of Generative AI: Engineering Trust, Interpretability, and Interaction Efficiency in Intelligent Systems

DOI:
https://doi.org/10.31875/2979-1081.2026.02.07
Submitted
July 5, 2026
Published
2026-07-05

Abstract

The proliferation of generative artificial intelligence (GenAI) systems has fundamentally transformed the landscape of human–machine communication (HMC). This paper examines three critical engineering dimensions of this transformation: trust calibration, interpretability mechanisms, and interaction efficiency. Drawing on recent advances in large language models (LLMs), conversational agents, and human–computer interaction (HCI) research, we analyze how these dimensions interrelate and affect overall system usability. We propose a conceptual framework—the TIE (Trust–Interpretability–Efficiency) model—that explicitly builds upon and extends established HCI usability models (ISO 9241-11; Nielsen, 1994) and AI trust taxonomies (Lee & See, 2004; Hoff & Bashir, 2015) to provide actionable design principles for GenAI communication systems. Novelty lies in the tripartite synthesis and the explicit modeling of interdependencies among cognitive trust, affective trust, behavioral reliance, multi-level interpretability (model-, system-, and interface-level), and operationally defined efficiency metrics. Our analysis indicates that trust and interpretability share a bidirectional dependency, while efficiency gains are contingent on users developing accurate mental models of AI capabilities. Ethical and governance dimensions—including accountability and misuse prevention—are integrated as co-equal design concerns. Applicability is primarily scoped to LLM-based conversational systems, with acknowledged limitations for multimodal and embodied AI. The paper concludes with a structured evaluation checklist and metric table to support practitioner utility.

References

  1. Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138-52160. https://doi.org/10.1109/ACCESS.2018.2870052
  2. Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., … Horvitz, E. (2019). Guidelines for human-AI interaction. Proceedings of CHI 2019. https://doi.org/10.1145/3290605.3300233
  3. Anthropic. (2023). Claude model card. Retrieved from https://www.anthropic.com/
  4. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., … Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82-115. https://doi.org/10.1016/j.inffus.2019.12.012
  5. Band, N., Lakshminarayanan, B., & Ghassemi, M. (2024). Linguistic uncertainty expression in large language models. Proceedings of ICLR 2024.
  6. Cai, C. J., Winter, S., Steier, D., Rabelo, L., & Terry, M. (2023). Hello AI: Uncovering the onboarding needs of medical clinicians for human-AI collaborative decision-making. ACM CHI Conference on Human Factors in Computing Systems.
  7. Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
  8. Hart, S. G., & Staveland, L. E. (1988). Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. Advances in Psychology, 52, 139-183. https://doi.org/10.1016/S0166-4115(08)62386-9
  9. Hoff, K. A., & Bashir, M. (2015). Trust in automation: Integrating empirical evidence on factors that influence trust. Human Factors, 57(3), 407-434. https://doi.org/10.1177/0018720814547570
  10. ISO. (2018). ISO 9241-11: Ergonomics of human-system interaction—Part 11: Usability: Definitions and concepts. International Organization for Standardization.
  11. Jakesch, M., Hancock, J. T., & Naaman, M. (2023). Human heuristics for AI-generated language are flawed. Proceedings of the National Academy of Sciences, 120(11). https://doi.org/10.1073/pnas.2208839120
  12. Jiang, J., et al. (2023). Interaction efficiency in large language model chat interfaces: An empirical analysis. Proceedings of CHI 2023.
  13. Kasirzadeh, A., & Gabriel, I. (2023). In conversation with artificial intelligence: Aligning language models with human values. Philosophy & Technology, 36(2), 1-24. https://doi.org/10.1007/s13347-023-00606-x
  14. Lee, J. D., & See, K. A. (2004). Trust in automation: Designing for appropriate reliance. Human Factors, 46(1), 50-80. https://doi.org/10.1518/hfes.46.1.50.30392
  15. Liao, Q. V., & Vaughan, J. W. (2023). AI transparency in the age of LLMs: A human-centered research roadmap. Harvard Data Science Review. https://doi.org/10.1162/99608f92.8036d03b
  16. Lipton, Z. C. (2018). The mythos of model interpretability. Queue, 16(3), 31-57. https://doi.org/10.1145/3236386.3241340
  17. Luger, E., & Sellen, A. (2016). “Like Having a Really Bad PA”: The Gulf between User Expectation and Experience of Conversational Agents. Proceedings of CHI 2016. https://doi.org/10.1145/2858036.2858288
  18. Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1-38. https://doi.org/10.1016/j.artint.2018.07.007
  19. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., … Gebru, T. (2019). Model cards for model reporting. Proceedings of the ACM Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3287560.3287596
  20. Nielsen, J. (1994). Usability Engineering. Academic Press. https://doi.org/10.1016/B978-0-08-052029-2.50007-3
  21. OpenAI. (2023). GPT-4 system card. Retrieved from https://openai.com/research/gpt-4
  22. Perez, F., & Ribeiro, I. (2022). Ignore previous prompt: Attack techniques for language models. arXiv preprint arXiv:2211.09527.
  23. Seshia, S. A., et al. (2023). Toward verified artificial intelligence. Communications of the ACM, 66(7), 86-98.
  24. Shanahan, M., McDonell, K., & Reynolds, L. (2023). Role play with large language models. Nature, 623, 493-498. https://doi.org/10.1038/s41586-023-06647-8
  25. Shum, H.-Y., He, X.-D., & Li, D. (2018). From Eliza to XiaoIce: Challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering, 19(1), 10-26. https://doi.org/10.1631/FITEE.1700826
  26. Steyvers, M., Tejeda, H., Kerrigan, G., & Smyth, P. (2023). Bayesian modeling of human-AI complementarity. Proceedings of the National Academy of Sciences, 119(11). https://doi.org/10.1073/pnas.2111547119
  27. Vaswani, A., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  28. Vossing, M., et al. (2022). Designing transparency for effective human-AI collaboration. Information Systems Frontiers, 24(3), 877-895. https://doi.org/10.1007/s10796-022-10284-3
  29. Wachter, S., Mittelstadt, B., & Russell, C. (2017). Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology, 31(2), 841-887. https://doi.org/10.2139/ssrn.3063289
  30. Weidinger, L., et al. (2022). Taxonomy of risks posed by language models. Proceedings of the ACM Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3531146.3533088
  31. Winograd, T., & Flores, F. (1986). Understanding Computers and Cognition. Norwood, NJ: Ablex Publishing.
  32. Woebbecke, G., Hauk, N., Siebers, M., & Buettner, R. (2024). Affective dimensions of trust in AI-mediated communication: A large-sample empirical study. Computers in Human Behavior, 152, 107988.
  33. Xu, Y., et al. (2023). Perceived agency and trust in conversational AI: A large-scale empirical study. ACM Transactions on Computer-Human Interaction, 30(2).