large language models

Beyond Known Speakers: Enhancing Spoofing Detection Generalization with VIVED

Recent speech synthesis systems have moved beyond conventional voice cloning toward the generation of expressive, text-described virtual identities. This shift creates a generalization challenge for spoofing countermeasures trained primarily on cloned speech from a limited pool of reference speakers and relatively neut...

Artificial intelligence transparency statements and publication governance in medical literature: cross-sectional analysis of 97,916 articles, 2015–2026

Large language models (LLMs) are increasingly used across scholarly writing, peer review, and editorial workflows, creating new research integrity questions about attribution, accountability, and disclosure. We measured how explicit artificial intelligence (AI) transparency statements are appearing in published medical...

URARI: Utility Rank Allocation and Residual Initialization — Implementation

This record provides the implementation of URARI (Utility Rank Allocation and Residual Initialization), a parameter-efficient fine-tuning method for code large language models. URARI combines task and semantic gradient signals to guide rank allocation under a fixed parameter budget and initializes additional low-rank d...

From equations to prompts: integrating LLMs into a hybrid macroeconomic ABM

Agent-based models (ABMs) typically rely on equations to incorporate agents' decision-making, ranging from ad-hoc rules or simple heuristics to complex, theory- or data-driven approaches. Recent advances in large language models (LLMs) make it possible to represent economic decision-making through information-condition...

Morphowiki: reusable agent-skill infrastructure for morphology-centered vocabulary knowledge construction

Large language models (LLMs) offer transformative capabilities for automated morphological analysis in language learning, yet their generated outputs typically remain fragmented within ephemeral chat interfaces, hindering systematic memory consolidation. To address this, we introduce Morphowiki, an open-source framewor...

Efficient Long-Context Reasoning in Large Language Models: Hierarchical Token Compression with Sparse Attention and Dynamic Memory Management

Bilal Syed Arfeen Research Corpus (Munafiq Protocol, Bayyinah, Furqan Lint, Structural Honesty Verification, Etc .) - AI Safety, Financial Analysis, Science, Theology

Bismillah. Dedicated to my cousins, Altamash Javed, Babar Javed Khan, Nadia Javed, Faisal Arfeen, Henna Arfeen, Osman Arfeen, Omer Arfeen, Salman Arfeen, and Saima Arfeen. May Allah swt protect them, their parents, and their children always, in sha Allah. Ameen ya Rabb. Alhamdulillah. These files are for anyone looking...

Structured Knowledge Graph for Scholarly Exploration: IR and QA System for ETDs and their Elements

Electronic Theses and Dissertations (ETDs) contain rich and detailed scholarly knowledge, but accessing that remains difficult. Conventional search systems largely operate at the document level and provide only coarse access to long-form academic writing. Though large language models (LLMs) can generate fluent response...

When Different Relational Experiences with AI Become Visible in Conversation: Linguistic and Dyadic Evidence from Naturalistic ChatGPT Interactions

People may experience large language models (LLMs) as therapeutically allied, emotionally close, or socially substitutive, but whether these relationships become visible in conversations is unknown. We distinguished what users discussed, what unfolded relationally, and how they experienced the AI relationship. We linke...

DTKF: a sepsis early prediction framework based on large language model semantic augmentation and dual-teacher knowledge distillation

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. Early and accurate prediction is crucial for reducing mortality. However, clinical settings often face challenges such as data scarcity, class imbalance, and the underutilization of unstructured clinical notes. Existing...

Qualia Algebra: A Mathematical Framework for Consciousness, from First Principles to Working Semantics

The measurement problem and the hard problem of consciousness share a structure: each derives the observer last and cannot account for what it finds there. Qualia Algebra (QA) inverts the order. From the one fact that survives total skepticism — I exist — it develops a grammar of manifestation (distinction, binding, at...

Drug Molecular and Route Similarity-Aware Retrieval-Augmented LLM Generation with Knowledge Graph for Semantic Reasoning

To address the inherent limitations of large language models (LLMs) in chemical synthesis—hallucinations, and low knowledge dense—this study presents a Knowledge Graph–enhanced Retrieval-Augmented Generation framework (KG-RAG-LLM) with a multi-scale calculation of molecular and route similarity. Empirical evaluations d...