CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
avril 2, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2604.01113v1 Announce Type: new Abstract: Large language model (LLM) systems are increasingly used to support...
Capturing Classic Authorial Style in Long-Form Story Generation with GRPO Fine-Tuning
février 4, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2512.05747v2 Announce Type: replace Abstract: Evaluating and optimising authorial style in long-form story generation remains...
Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry
octobre 20, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2510.15313v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to creative domains...
CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese
novembre 7, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2511.04139v1 Announce Type: new Abstract: Automatic speech recognition (ASR) is critical for language accessibility, yet...
Can We Trust Machine Learning? The Reliability of Features from Open-Source Speech Analysis Tools for Speech Modeling
juin 16, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2506.11072v1 Announce Type: cross Abstract: Machine learning-based behavioral models rely on features extracted from audio-visual...
Can We Trust LLM’s Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
juillet 11, 2026admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2607.08017v1 Announce Type: new Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful...
Can We Improve Llama 3’s Reasoning Through Post-Training Alone? ASTRO Shows +16% to +20% Benchmark Gains
juillet 5, 2025admin NUAI,Committee,Actualités,Uncategorized(0)Improving the reasoning capabilities of large language models (LLMs) without architectural changes is a core...
Can Vision Language Models Infer Human Gaze Direction? A Controlled Study
juin 9, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2506.05412v1 Announce Type: cross Abstract: Gaze-referential inference–the ability to infer what others are looking at–is...
Can structural correspondences ground real world representational content in Large Language Models?
juin 23, 2025admin NUAI,Committee,Actualités,Uncategorized(0)arXiv:2506.16370v1 Announce Type: new Abstract: Large Language Models (LLMs) such as GPT-4 produce compelling responses...
