Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction
septembre 19, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2509.14504v1 Announce Type: new Abstract: In this paper, we introduce OmniGEC, a collection of multilingual...
Interpreting the Latent Structure of Operator Precedence in Language Models
octobre 17, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.13908v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities but...
Interpretable Text Classification: Probing Scikit-LLM Embedding Spaces
août 29, 2026admin NUAI,Committee,Actualités,Uncategorized(0)In this article, you will learn how to use probing classifiers, UMAP visualization, and SHAP...
Interpretable Text Classification: Probing Scikit-LLM Embedding Spaces
août 29, 2026admin NUAI,Committee,Actualités,Uncategorized(0)In this article, you will learn how to use probing classifiers, UMAP visualization, and SHAP...
Interpretable Question Answering with Knowledge Graphs
octobre 23, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.19181v1 Announce Type: new Abstract: This paper presents a question answering system that operates exclusively...
Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
septembre 1, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2507.05137v2 Announce Type: replace Abstract: Learning Japanese vocabulary is a challenge for learners from Roman...
InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
octobre 27, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.21538v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet...
Internal World Models as Imagination Networks in Cognitive Agents
octobre 7, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.04391v1 Announce Type: cross Abstract: What is the computational objective of imagination? While classical interpretations...
Internal Coherence Maximization (ICM): A Label-Free, Unsupervised Training Framework for LLMs
juin 15, 2025admin NUAI,Committee,Actualités,Uncategorized(0)Post-training methods for pre-trained language models (LMs) depend on human supervision through demonstrations or preference...
