Science ❯ Computer Science ❯ Artificial Intelligence ❯ Machine Learning

Large Language Models

Two New RAG Preprints Propose Theme-Aligned Hypergraphs and Hierarchical Agents

The authors report gains over strong baselines, with claims posted as unreviewed preprints.

New Research Maps LLM Strengths and Failures, Advancing Practical Fixes for Reliability, Privacy and Cost

Study Finds LLMs Obey Illogical Medical Requests as New Benchmarks Expose Wider Reasoning Gaps

LLM-Agent Research Coalesces Around Generalizability, RLVR, and Grounded Retrieval

New RAG Preprints Propose Retrieval, Reasoning, and Graph Methods to Curb Hallucinations

NYU Confirms 'PromptLock' as Lab-Built LLM Ransomware Prototype After ESET Discovery

LLM Vulnerabilities Drive Emergence of Self-Improving AI Frameworks