Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge
6 月 26, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2606.26511v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but...
Temporal Analysis of Climate Policy Discourse: Insights from Dynamic Embedded Topic Modeling
7 月 10, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2507.06435v1 Announce Type: new Abstract: Understanding how policy language evolves over time is critical for...
Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs
1 月 15, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2404.03471v5 Announce Type: replace Abstract: Bias in large language models (LLMs) has many forms, from...
Technology Innovation Institute TII Releases Falcon-H1: Hybrid Transformer-SSM Language Models for Scalable, Multilingual, and Long-Context Understanding
5 月 22, 2025admin NUAI,Committee,新闻,Uncategorized(0)Addressing Architectural Trade-offs in Language Models As language models scale, balancing expressivity, efficiency, and adaptability...
Techniques for supercharging academic writing with generative AI
6 月 23, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2310.17143v4 Announce Type: replace-cross Abstract: Academic writing is an indispensable yet laborious part of the...
Tech researchers are suing the Trump administration over the future of online safety
5 月 21, 2026admin NUAI,Committee,新闻,Uncategorized(0)Since its earliest days back in office, the Trump administration has been going after researchers...
Team “better_call_claude”: Style Change Detection using a Sequential Sentence Pair Classifier
8 月 4, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.00675v1 Announce Type: new Abstract: Style change detection – identifying the points in a document...
Teaching the model: Designing LLM feedback loops that get smarter over time
8 月 17, 2025admin NUAI,Committee,新闻,Uncategorized(0)How to close the loop between user behavior and LLM performance, and why human-in-the-loop systems...
Teaching AI to Say ‘I Don’t Know’: A New Dataset Mitigates Hallucinations from Reinforcement Finetuning
6 月 6, 2025admin NUAI,Committee,新闻,Uncategorized(0)Reinforcement finetuning uses reward signals to guide the large language model toward desirable behavior. This...
