technocracy

arXiv:2603.03320v1 Announce Type: new Abstract: Effective communication often relies on aligning a message with an audience’s narrative and worldview. Narrative shift involves transforming text to reflect a different narrative framework while preserving its original core message–a task we demonstrate is significantly challenging for current Large Language Models (LLMs). To address this, we propose a neurosymbolic approach grounded in social science theory and abductive reasoning. Our method automatically extracts rules to abduce the specific story elements needed to guide […]

Ver mais

arXiv:2604.07518v1 Announce Type: new Abstract: Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to extract semantics in multi-step reasoning. We propose emph{“Decompose, Look, and Reason” (DLR)}, a reinforced latent reasoning framework that dynamically decomposes queries into textual premises, extracts premise-conditioned continuous visual latents, and deduces answers through grounded rationales. We introduce […]

Ver mais

Digital Trust Is Not a Feature – It’s a Philosophical Problem For most of human history, trust was something we negotiated face to face. We trusted people we knew, institutions we could see, and systems that evolved slowly enough for social norms to keep pace. Today, that foundation is gone. Trust now flows through code, algorithms, platforms, and automated decisions – often invisible, often opaque, and rarely negotiable. This is not merely a technological shift. It is ==a […]

Ver mais

arXiv:2601.14417v1 Announce Type: new Abstract: Many spoken languages, including English, exhibit wide variation in dialects and accents, making accent control an important capability for flexible text-to-speech (TTS) models. Current TTS systems typically generate accented speech by conditioning on speaker embeddings associated with specific accents. While effective, this approach offers limited interpretability and controllability, as embeddings also encode traits such as timbre and emotion. In this study, we analyze the interaction between speaker embeddings and linguistically motivated phonological rules […]

Ver mais

I finally did it. Last week, I built a prompt that generated a flawless documentation site from a GitHub repo. It was beautiful. I felt like a wizard. I even bookmarked it as my “Gold Standard” prompt. Then, yesterday happened. I ran the exact same prompt on a new repo—similar structure, similar size—and it was a total disaster. The AI started ignoring the CSS requirements, forgot to link the sub-pages, and kept trying to write the docs in […]

Ver mais

arXiv:2602.22925v1 Announce Type: new Abstract: We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian-process limits. Large-deviation theory provides explicit variational objectives-rate functions-on predictors, providing an emerging notion of complexity and feature learning directly at the functional level. We show that the posterior output rate function is obtained by a joint optimization over predictors and internal kernels, in contrast with fixed-kernel (NNGP) theory. Numerical experiments demonstrate that the […]

Ver mais

arXiv:2601.00086v2 Announce Type: new Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows. This highlights the need for effective adaptation to task-specific tools. We propose RIMRULE, a neuro-symbolic approach for LLM adaptation based on dynamic rule injection. Compact, interpretable rules are distilled from failure traces and injected into the prompt during inference to improve task performance. These rules are proposed by the […]

Ver mais

arXiv:2603.02333v1 Announce Type: new Abstract: Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a competitive alternative, yet their memorization behavior remains largely unexplored due to fundamental differences in generation dynamics. To address this gap, we present a systematic theoretical and empirical characterization of memorization in DLMs. We propose a generalized probabilistic extraction framework that unifies prefix-conditioned […]

Ver mais

arXiv:2601.20999v1 Announce Type: new Abstract: Phishing attacks through text, also known as smishing, are a prevalent type of social engineering tactic in which attackers impersonate brands to deceive victims into providing personal information and/or money. While smishing awareness and cyber education are a key method by which organizations communicate this awareness, the guidance itself varies widely. In this paper, we investigate the state of practice of how 149 well-known brands across 25 categories educate their customers about smishing […]

Ver mais