A Confidence Signal after Perception and Reasoning Are Merged

Authors

  • Cameron Barker Author
  • Edward Morris Author
  • Ryan Rhodes Author

Abstract

Model merging can preserve an aggregate score while changing the behavior of an internal risk alert. Evaluation should freeze model variants and test modality-specific grounding and alert calibration separately. The action triggered by an alert needs its own outcome comparison. A useful development-file correlation does not establish the benefit of a mitigation workflow after merging. This focused synthesis develops an empirical comparison that preserves the terminal action, observation process, and total verification cost. Its proposed tests are prospective; no new simulation run, model-training result, or intervention effect is reported.

References

  1. S. Chen, J. Zhang, T. Zhu, W. Liu, S. Gao, M. Xiong, M. Li, and J. He, “Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging,” Proceedings of the 42nd International Conference on Machine Learning, 2025.
  2. S. Chen, M. Xiong, J. Liu, Z. Wu, T. Xiao, S. Gao, and J. He, “In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation,” Proceedings of the 41st International Conference on Machine Learning, 2024.
  3. Zhou, Yongxi, Wenbo Ye, Yuanzhe Liu, Zihan Dong, and Junwei Yao. “Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts.” arXiv, 2026, arXiv:2609.08236. https://arxiv.org/abs/2609.08236.
  4. Sang, Yinghao. “AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought.” 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA), IEEE, 2025, pp. 1177-1180. https://doi.org/10.1109/icmlca66850.2025.11336788.
  5. Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. 2nd ed., MIT Press, 2018. http://incompleteideas.net/book/the-book-2nd.html.
  6. Levine, Sergey, Aviral Kumar, George Tucker, and Justin Fu. “Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.” arXiv, 2020, arXiv:2005.01643. https://arxiv.org/abs/2005.01643.
  7. Kumar, Aviral, Aurick Zhou, George Tucker, and Sergey Levine. “Conservative Q-Learning for Offline Reinforcement Learning.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1179–1191. https://arxiv.org/abs/2006.04779.
  8. Lewis, Patrick, et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. https://arxiv.org/abs/2005.11401.
  9. Geifman, Yonatan, and Ran El-Yaniv. “Selective Classification for Deep Neural Networks.” Advances in Neural Information Processing Systems, vol. 30, 2017. https://arxiv.org/abs/1705.08500.
  10. Ovadia, Yaniv, et al. “Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift.” Advances in Neural Information Processing Systems, vol. 32, 2019. https://arxiv.org/abs/1906.02530.
  11. Bertsimas, Dimitris, and Melvyn Sim. “The Price of Robustness.” Operations Research, vol. 52, no. 1, 2004, pp. 35–53. https://doi.org/10.1287/opre.1030.0065.
  12. Rasmussen, Carl Edward, and Christopher K. I. Williams. Gaussian Processes for Machine Learning. MIT Press, 2006. https://gaussianprocess.org/gpml/.

Downloads

Published

2025-12-02

Versions

Issue

Vol. 1 No. 12 (2025): December 2025

Section

Articles