arXiv:2608.14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions–enterprise policies, PII redlines, tool boundaries–that vary per request and per tenant. Conventional post-training is structurally ill-suited: SFT hides the violation signal in compliant labels, and DPO’s sequence-level…
arXiv:2509.25459v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. However, in long-form scientific question answering, LLMs often hallucinate, producing unsupported or inconsistent claims. Retrieval-Augmented Generation (RAG)…
arXiv:2608.14645v1 Announce Type: new Abstract: Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates spaceborne measurements with improved revisit frequency and spatial coverage. In this context, the Horizon…
arXiv:2605.20281v2 Announce Type: replace-cross Abstract: We develop a unified microeconomic and monetary theory of artificial intelligence inference costs and their pass-through to inflation, welfare, and optimal monetary policy. We introduce the Inference-Cost Phillips Curve (ICPC), an augmented New Keynesian Phillips…
arXiv:2608.14646v1 Announce Type: new Abstract: Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reasoning. This paper introduces iFuzz-Meta, an interpretable fuzzy rule-based learning…
arXiv:2608.15362v1 Announce Type: cross Abstract: We propose a methodology based on the standard ReLU Deep Neural Networks (DNN) to make predictions and quantify their uncertainty. Classically, people rely on linear, non-linear, or non-parametric kernel methods to fit and then predict…
arXiv:2608.14647v1 Announce Type: new Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective…
arXiv:2608.15689v1 Announce Type: cross Abstract: This study presents a hybrid epidemiological and behavioural framework to simulate the spread of health misinformation on social media. We extend the classical Susceptible–Infected–Recovered (SIR) model to a six-compartment structure (SIRMMM), incorporating Misinformed Susceptible (MS),…
arXiv:2608.14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candidate label, it asks a short yes/no question and compares the probabilities of the two answer tokens…
arXiv:2608.15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial…
