Feedback Indicators: The Alignment between Llama and a Teacher in Language Learning
Agosto 18, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2508.11364v1 Announce Type: new Abstract: Automated feedback generation has the potential to enhance students’ learning...
Fastino Releases GLiNER2.5: A Boundary-Prediction Architecture That Removes Span Enumeration From Information Extraction
Agosto 25, 2026admin NUAI,Committee,Notizie,Uncategorized(0)Information extraction teams face a recurring choice. Small encoder models are cheap but rigid, and...
Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs
Marzo 4, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2603.02830v1 Announce Type: new Abstract: Predicting future student responses to questions is particularly valuable for...
Faster and Better LLMs via Latency-Aware Test-Time Scaling
Settembre 15, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2505.19634v4 Announce Type: replace Abstract: Test-Time Scaling (TTS) has proven effective in improving the performance...
FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation–Full Version
Aprile 8, 2026admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2604.05551v1 Announce Type: new Abstract: Self-conditioning has been central to the success of continuous diffusion...
Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
Agosto 19, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2508.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in reasoning...
FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
Maggio 14, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2505.08054v1 Announce Type: new Abstract: Safety alignment approaches in large language models (LLMs) often lead...
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
Settembre 5, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2509.03888v1 Announce Type: new Abstract: Large Language Models (LLMs) can comply with harmful instructions, raising...
Falcon: A Comprehensive Chinese Text-to-SQL Benchmark for Enterprise-Grade Evaluation
Ottobre 30, 2025admin NUAI,Committee,Notizie,Uncategorized(0)arXiv:2510.24762v1 Announce Type: new Abstract: We introduce Falcon, a cross-domain Chinese text-to-SQL benchmark grounded in...
