相关论文: Structural Rigidity and the 57-Token Predictive Wi…

We propose a neuro-symbolic architecture that learns four interpretable physiological concepts, oculomotor dynamics, gaze stability, prefrontal hemodynamics, and multimodal, from eye-tracking and neural hemodynamics, functional…

Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…

Machine learning systems in fraud detection, credit scoring, and clinical risk assessment operate under delayed ground truth: outcome labels arrive days to months after the decision they evaluate. During this blind period, governance…

Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This degradation has been measured behaviorally but not…

Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing…

Governance theory has quietly relied on a rough cognitive comparability between governors and governed. The assumption is load-bearing, and this paper tries to show why by making it testable. The vehicle is a six-dimension evaluation…

Artificial intelligence systems are increasingly deployed in high-stakes domains, yet it remains unclear whether existing governance frameworks ensure accountability after deployment. This study makes two contributions. First, it presents a…

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Risk decision systems in fraud detection and credit scoring operate under structural label absence: ground truth arrives weeks to months after decisions are made. During this blind period, model performance may degrade silently, eroding the…

We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying…

This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing…

This article introduces the concept of the algorithmic unconscious to designate the set of structural determinations that operate within large language models (LLMs) without being accessible either to the model's own reflexivity or to that…

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Understanding learners' cognitive and affective states underpins adaptive educational systems and effective teaching. Although research links nonverbal cues to internal states, no framework calibrates them to evidence. We present the…

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency,…

Agentic AI systems plan, use tools, maintain state, and act across multi-step workflows with external effects, meaning trustworthy deployment can no longer be judged by task completion alone. The current literature remains fragmented across…

We introduce energy-based constraint networks -- a modality-agnostic architecture that learns structural coherence from contrastive pairs. The system processes frozen encoder embeddings through a state-space model with dual-head attention,…

Autoregressive transformers make confident errors that output-confidence monitoring cannot catch. Activation monitors catch them only when training leaves a decision-quality signal beyond what the output already exposes. This signal is an…

Computational fluid dynamics (CFD)-driven machine learning frameworks based on symbolic regression offer a promising pathway for turbulence model discovery, but are often hindered by numerical instability, residual stagnation, and…