LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
junio 27, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2505.00753v4 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have sparked growing...
LLM-as-a-Judge: Where Do Its Signals Break, When Do They Hold, and What Should “Evaluation” Mean?
septiembre 21, 2025admin NUAI,Committee,Noticias,Uncategorized(0)What exactly is being measured when a judge LLM assigns a 1–5 (or pairwise) score?...
LLM-as-a-Judge: Can Language Models Be Trusted to Evaluate Other Models?
abril 30, 2025admin NUAI,Committee,Noticias,Uncategorized(0)Exploring the promise, pitfalls, and practical applications of using LLMs to automate AI evaluation — from synthetic...
LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation
junio 16, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.11237v1 Announce Type: cross Abstract: In an effort to automatically evaluate and select the best...
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
enero 29, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2510.13907v2 Announce Type: replace Abstract: Large language models (LLMs) are highly sensitive to prompts, but...
LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS
noviembre 5, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2511.02089v1 Announce Type: cross Abstract: Contrast-Consistent Search (CCS) is an unsupervised probing method able to...
LLM Orchestration Frameworks Compared: LangChain vs. LlamaIndex vs. Raw API Calls
julio 9, 2026admin NUAI,Committee,Noticias,Uncategorized(0)The default assumption in most LLM developer communities is that you start with raw API...
LLM or Human? Perceptions of Trust and Information Quality in Research Summaries
enero 23, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2601.15556v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to generate and...
LLM one-shot style transfer for Authorship Attribution and Verification
octubre 16, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2510.13302v1 Announce Type: new Abstract: Computational stylometry analyzes writing style through quantitative patterns in text...
