Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation
January 28, 2026admin NUAI,Committee,News,Uncategorized(0)arXiv:2601.19350v1 Announce Type: new Abstract: Traditional metrics like BLEU and BERTScore fail to capture semantic...
Cross-Domain Data Selection and Augmentation for Automatic Compliance Detection
April 24, 2026admin NUAI,Committee,News,Uncategorized(0)arXiv:2604.21469v1 Announce Type: new Abstract: Automating the detection of regulatory compliance remains a challenging task...
Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
October 15, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2510.12137v1 Announce Type: new Abstract: Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident...
Creativity in AI: Progresses and Challenges
July 1, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2410.17218v5 Announce Type: replace-cross Abstract: Creativity is the ability to produce novel, useful, and surprising...
Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models
May 1, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2504.21026v1 Announce Type: new Abstract: With the growing presence of multilingual users on social media...
Crawlee for Python: Build a Web Crawling Pipeline with Robots Handling, Link Graphs, and RAG Chunk Export
June 21, 2026admin NUAI,Committee,News,Uncategorized(0)In this tutorial, we build a full Crawlee-for-Python workflow that covers environment setup, local website...
Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM
December 16, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2512.12868v1 Announce Type: new Abstract: Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks...
Counterfactual LLM-based Framework for Measuring Rhetorical Style
December 24, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2512.19908v1 Announce Type: new Abstract: The rise of AI has fueled growing concerns about “hype”...
CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought
June 4, 2025admin NUAI,Committee,News,Uncategorized(0)arXiv:2502.17214v2 Announce Type: replace Abstract: Large language models (LLMs) excel in many tasks but struggle...
