Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models
5月 1, 2025admin NUAI,Committee,ニュース,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
6月 21, 2026admin NUAI,Committee,ニュース,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
12月 16, 2025admin NUAI,Committee,ニュース,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
12月 24, 2025admin NUAI,Committee,ニュース,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
6月 4, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2502.17214v2 Announce Type: replace Abstract: Large language models (LLMs) excel in many tasks but struggle...
CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
9月 26, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.04027v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has become a pivotal approach for enhancing...
CoSyn: The open-source tool that’s making GPT-4V-level vision AI accessible to everyone
7月 26, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Researchers at the University of Pennsylvania and the Allen Institute for Artificial Intelligence have developed...
CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
2月 6, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2507.04756v3 Announce Type: replace Abstract: Personalization has become crucial for adapting models to the diverse...
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
11月 10, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2511.05359v1 Announce Type: cross Abstract: As language models evolve into autonomous agents that act and...
