February 2026

arXiv:2602.11179v1 Announce Type: new Abstract: Prompt engineering has emerged as an integral technique for extending the strengths and abilities of Large Language Models (LLMs) to gain significant performance gains in various Natural Language Processing (NLP) tasks. This approach, which requires instructions to be composed in natural language to bring out the knowledge from LLMs in a structured way, has driven breakthroughs in various NLP tasks. Yet there is still no structured framework or coherent understanding of the varied […]

Ver mais

arXiv:2602.11177v1 Announce Type: new Abstract: Reliable early detection of Alzheimer’s disease (AD) is challenging, particularly due to limited availability of labeled data. While large language models (LLMs) have shown strong transfer capabilities across domains, adapting them to the AD domain through supervised fine-tuning remains largely unexplored. In this work, we fine-tune an LLM for AD detection and investigate how task-relevant information is encoded within its internal representations. We employ probing techniques to analyze intermediate activations across transformer layers, […]

Ver mais

arXiv:2602.11176v1 Announce Type: new Abstract: Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration, where adaptive systems must respond to human activities. Existing data-driven agent-based models–from rule-based to deep learning–struggle in low-data environments, limiting their practicality. This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap by reasoning about everyday activities from compact contextual cues. […]

Ver mais

arXiv:2602.11175v1 Announce Type: new Abstract: Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations in discrete reasoning tasks, such as arithmetic, logical inference, and algorithmic composition, remain a critical open problem. In this survey, we synthesize recent studies from three theoretical perspectives: circuit complexity, approximation theory, and communication complexity, to clarify the structural and computational barriers that transformers face […]

Ver mais

arXiv:2602.11174v1 Announce Type: new Abstract: Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical linguistic content. Across mBERT and XLM-R, the higher-fragmentation orthography shows a ~3.4x increase in fertility (6.73-6.85 vs. 2.10-2.35 tokens/word), leading to a 16.5x inference slowdown (0.23 vs. 3.8 sentences/second) on identical hardware. Using bits per character (BPC) to avoid the […]

Ver mais

arXiv:2602.11173v1 Announce Type: new Abstract: Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. Recent work frames this task as automatic text generation, underusing author expertise and intent. In practice, authors possess domain expertise, author-only information, revision and response strategies–concrete forms of author expertise and intent–to address reviewer concerns, and seek NLP assistance that integrates these signals to support effective response writing in peer review. We reformulate author response generation […]

Ver mais

arXiv:2602.11172v1 Announce Type: new Abstract: Legal advocacy requires a unique combination of authoritative tone, rhythmic pausing for emphasis, and emotional intelligence. This study investigates the performance of the Gemini 2.5 Flash TTS and Gemini 2.5 Pro TTS models in generating synthetic courtroom speeches across five Indic languages: Tamil, Telugu, Bengali, Hindi, and Gujarati. We propose a prompting framework that utilizes Gemini 2.5s native support for 5 languages and its context-aware pacing to produce distinct advocate personas. The evolution […]

Ver mais

arXiv:2602.11171v1 Announce Type: new Abstract: Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enables resource-efficient personalization or specialization, but it comes at the expense of additional hyperparameter tuning. Although LoRA makes fine-tuning efficient, it is highly sensitive to the choice of hyperparameters, and exhaustive hyperparameter search is still computationally very demanding. To address these challenges, we propose a framework that integrates the domain knowledge of pre-trained LLMs into Bayesian Optimization (BO) to efficiently search for LoRA hyperparameters. […]

Ver mais

arXiv:2602.11170v1 Announce Type: new Abstract: Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative Multi-agent Execution), a framework comprising three specialized agents, an executor for step-by-step reasoning, a verifier for constraint checking, and a coordinator for backtracking control, optimized through group relative policy optimization. For comprehensive evaluation, we introduce PRIME-Bench, the largest algorithmic reasoning benchmark to date, comprising 86 […]

Ver mais

arXiv:2602.11169v1 Announce Type: new Abstract: Transformer hidden states encode information as high-dimensional vectors, yet whether direction (orientation in representational space) and magnitude (vector norm) serve distinct functional roles remains unclear. Studying Pythia-family models, we discover a striking cross-over dissociation: angular perturbations cause up to 42.9 more damage to language modeling loss, while magnitude perturbations cause disproportionately more damage to syntactic processing (20.4% vs.1.6% accuracy drop on subject-verb agreement).This finding is enabled by L2-matched perturbation analysis, a methodology ensuring […]

Ver mais