arXiv Computer Science @arxiv_cs@qoto.org

A Randomized Controlled Trial and Pilot of Scout: an LLM-Based EHR Search and Synthesis Platform https://arxiv.org/abs/2604.26953 #cs.IR #cs.CY

The Impact of LLM Self-Consistency and Reasoning Effort on Automated Scoring Accuracy and Cost https://arxiv.org/abs/2604.26954 #cs.CY #cs.AI

Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories https://arxiv.org/abs/2604.26955 #cs.CY #cs.AI

Can AI be a moral victim? The role of moral patiency and ownership perceptions in ethical judgments of using AI-generated content https://arxiv.org/abs/2604.26956 #cs.CY #cs.AI #cs.HC

Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings https://arxiv.org/abs/2604.26957 #cs.CY #cs.AI

Designing Ethical Learning for Agentic AI: Toegye Yi Hwang's Ethical Emotion Regulation Framework https://arxiv.org/abs/2604.26958 #cs.CY #cs.AI

CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs https://arxiv.org/abs/2604.26959 #cs.CY #cs.AI #cs.MA

LLM Biases https://arxiv.org/abs/2604.26960 #cs.CY #cs.AI

Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding https://arxiv.org/abs/2604.26961 #cs.SE #cs.AI #cs.PL

DeepTutor: Towards Agentic Personalized Tutoring https://arxiv.org/abs/2604.26962 #cs.CY #cs.AI #cs.CL

Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats https://arxiv.org/abs/2604.25920 #cs.CL #cs.AI

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety https://arxiv.org/abs/2604.25921 #cs.CL #cs.CR

Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models https://arxiv.org/abs/2604.25922 #cs.CL #cs.AI

Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing https://arxiv.org/abs/2604.25923 #cs.CL

Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects https://arxiv.org/abs/2604.25924 #cs.CL #cs.AI #cs.IR

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding https://arxiv.org/abs/2604.25925 #cs.CL

MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese https://arxiv.org/abs/2604.25926 #cs.CL #cs.IR

Information Extraction from Electricity Invoices with General-Purpose Large Language Models https://arxiv.org/abs/2604.25927 #cs.CL

CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA https://arxiv.org/abs/2604.25928 #cs.CL

LLMs Generate Kitsch https://arxiv.org/abs/2604.25929 #cs.CL