arXiv Computer Science @arxiv_cs@qoto.org

LATTS: Locally Adaptive Test-Time Scaling https://arxiv.org/abs/2509.20368 #cs.AI

AI-driven formative assessment and adaptive learning in data-science education: Evaluating an LLM-powered virtual teaching assistant https://arxiv.org/abs/2509.20369 #cs.CY #cs.AI #cs.HC

Philosophy-informed Machine Learning https://arxiv.org/abs/2509.20370 #cs.AI #cs.CY #cs.LG

Speaker Style-Aware Phoneme Anchoring for Improved Cross-Lingual Speech Emotion Recognition https://arxiv.org/abs/2509.20373 #cs.CL #cs.LG

CFD-LLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics https://arxiv.org/abs/2509.20374 #cs.CL #cs.AI

Assessing Classical Machine Learning and Transformer-based Approaches for Detecting AI-Generated Research Text https://arxiv.org/abs/2509.20375 #cs.CL #cs.AI

ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models https://arxiv.org/abs/2509.20376 #cs.CL #cs.AI

SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation https://arxiv.org/abs/2509.20377 #cs.CL #cs.AI

Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning https://arxiv.org/abs/2509.19305 #eess.SP #cs.LG #cs.AI

Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias https://arxiv.org/abs/2509.19314 #cs.CL #cs.AI #cs.CY

FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering https://arxiv.org/abs/2509.19319 #cs.CL #cs.AI

Readme_AI: Dynamic Context Construction for Large Language Models https://arxiv.org/abs/2509.19322 #cs.CL #cs.AI

Magnitude Matters: a Superior Class of Similarity Metrics for Holistic Semantic Understanding https://arxiv.org/abs/2509.19323 #cs.CL #cs.AI

How Much of Your Data Can Suck? Thresholds for Domain Performance and Emergent Misalignment in LLMs https://arxiv.org/abs/2509.19325 #cs.CL

Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers https://arxiv.org/abs/2509.19326 #cs.CL #cs.AI

A systematic review of trial-matching pipelines using large language models https://arxiv.org/abs/2509.19327 #cs.CL #cs.AI

How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment https://arxiv.org/abs/2509.19329 #stat.ME #cs.CL

Quantifying Compositionality of Classic and State-of-the-Art Embeddings https://arxiv.org/abs/2509.19332 #cs.CL #cs.AI

Stochastic Economic Dispatch with Battery Energy Storage considering Wind and Load Uncertainty https://arxiv.org/abs/2509.18100 #eess.SY #cs.SY

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services https://arxiv.org/abs/2509.18101 #cs.AI #cs.LG