False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs
High-confidence errors in large language models are often treated as fragile failures. We study an alternative: some errors may be false fixed points, locally stable, internally coherent, and confidently wrong. This separates robustness from truth-tracking. We develop the separation through a Kantian commitment-gate framing and a minimal linear feedback model in which stability and correctness can diverge. Across three open-weight models, overconfident wrong items are not systematically more locally fragile than confidently correct items under our hidden-state sensitivity probes. Abstention-aware self-critique reduces overconfident wrong commitments by sacrificing coverage, and C3-R, a rule-based explicit feedback gate, sharpens that tradeoff rather than eliminating it. These results motivate, but do not establish, high signal-to-noise (high-SNR) inertia and representational compression as possible mechanisms for stable miscalibration.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sora and V-JEPA Have Not Learned The Complete Real World Model -- A Philosophical Analysis of Video AIs Through the Theory of Productive Imagination
Sora from Open AI has shown exceptional performance, yet it faces scrutiny over whether its technological prowess equates to an authentic comprehension of reality. Critics contend that it lacks a foundational grasp of th…
PhilosophyKantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics
Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequences of action. Understanding that despite …
Action UnderstandingEthicsFairnessStable fixed points of combinatorial threshold-linear networks
Combinatorial threshold-linear networks (CTLNs) are a special class of recurrent neural networks whose dynamics are tightly controlled by an underlying directed graph. Recurrent networks have long been used as models for…
Analysis and Mitigation of Data injection Attacks against Data-Driven Control
This paper investigates the impact of false data injection attacks on data-driven control systems. Specifically, we consider an adversary injecting false data into the sensor channels during the learning phase. When the …
Game-theoretic Models of Moral and Other-Regarding Agents
We investigate Kantian equilibria in finite normal form games, a class of non-Nashian, morally motivated courses of action that was recently proposed in the economics literature. We highlight a number of problems with su…
Form