Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench
4 月 7, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2604.03455v1 Announce Type: cross Abstract: Retrieval-Augmented Generation pipelines span a wide range of retrieval strategies...
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence
12 月 5, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.04578v1 Announce Type: new Abstract: Legal general intelligence (GI) refers to artificial intelligence (AI) that...
Leveraging Machine Learning to Identify Gendered Stereotypes and Body Image Concerns on Diet and Fitness Online Forums
12 月 11, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2407.03551v2 Announce Type: replace-cross Abstract: The pervasive expectations about ideal body types in Western society...
Let’s Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM’s Math Capability
10 月 14, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.23703v4 Announce Type: replace-cross Abstract: Enhancing the mathematical reasoning capabilities of LLMs has garnered significant...
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
1 月 14, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2601.08682v1 Announce Type: new Abstract: Summarization of multi-party dialogues is a critical capability in industry...
Less Is More for Multi-Step Logical Reasoning of LLM Generalisation Under Rule Removal, Paraphrasing, and Compression
12 月 15, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.06393v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance on many natural...
Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
7 月 3, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2507.02964v2 Announce Type: replace Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC)...
LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text
6 月 2, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.24826v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in legal...
Learning to lead in a hybrid human-AI enterprise
6 月 9, 2026admin NUAI,Committee,新闻,Uncategorized(0)As adoption of AI agents looks set to surge by as much as 300% in...
