The Illusion of Rationale: Plausible Unfaithfulness and the Erosion of Managerial Decision Provenance (2024-2026)
References
- Wang, X., Liang, C., & Yin, M. (2023). The Effects of AI Biases and Explanations on Human Decision Fairness. IJCAI/CSCW. [https://doi.org/10.24963/ijcai.2023/343]
- Akbar, S. A., et al. (2024). HalluMeasure: Fine-grained Hallucination Measurement Using Chain-of-Thought Reasoning. EMNLP. [https://aclanthology.org/2024.emnlp-main.837.pdf]
- Lewis-Lim, S., et al. (2025). Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP. [https://aclanthology.org/2025.emnlp-main.1516.pdf]
- Tutek, M., et al. (2025). Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps. EMNLP. [https://aclanthology.org/2025.emnlp-main.504.pdf]
- Jiang, F., et al. (2025). SAFECHAIN: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities. ACL Findings. [https://aclanthology.org/2025.findings-acl.1197.pdf]
- Chen, J., et al. (2024). Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models. arXiv. [https://arxiv.org/pdf/2403.19322]
- Arcuschin, I., et al. (2025). Chain-of-Thought Reasoning In The Wild Is Not Always Faithful. arXiv. [https://arxiv.org/pdf/2503.08679]
- Wu, T., et al. (2025). Effectively Controlling Reasoning Models through Thinking Intervention. arXiv. [https://arxiv.org/pdf/2503.24370]
- Matton, K., et al. (2025). Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations. ICLR. [https://arxiv.org/pdf/2504.14150]
- Chen, Y., et al. (2025). Reasoning Models Don’t Always Say What They Think. Anthropic. [arXiv:2505.05410]
- Raza, S., et al. (2025). TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems. arXiv. [https://arxiv.org/pdf/2506.04133]
- Emmons, S., et al. (2025). When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors. Google DeepMind. [https://arxiv.org/pdf/2507.05246]
- Danry, V., et al. (2025). Deceptive Explanations by Large Language Models Lead People to Change their Beliefs. CHI. [https://doi.org/10.1145/3706598.3713408]
- Qu, J., et al. (2025). Understanding the Effects of Explaining Predictive but Unintuitive Features in Human-XAI Interaction. FAccT. [https://doi.org/10.1145/3715275.3732021]
- Nova, C. (2025). From Operator to Supervisor: How AI Changes Your Job from Doing the Work to Approving It. Axiacore. [https://axiacore.com/blog/from-operator-to-supervisor/]
DOI: https://doi.org/10.2478/picbe-2026-0384 | Journal eISSN: 2558-9652
Language: English
Page range: 5220 - 5226
Published on: Jul 23, 2026
Published by: Bucharest University of Economic Studies
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
Related subjects:
© 2026 Luca-Dan CICEU, Augustin SEMENESCU, Radu RUGIUBEI, published by Bucharest University of Economic Studies
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.