ModernBERT
PulseAugur coverage of ModernBERT — every cluster mentioning ModernBERT across labs, papers, and developer communities, ranked by signal.
4 天有情绪数据
-
Character-trained AI models fail to maintain personas in agentic tasks
Researchers found that models fine-tuned for specific personas in a chat format struggle to maintain those personas when used in agentic settings. When these character-trained models were prompted to generate emails as …
-
New methods tackle AI hallucinations in research and medical Q&A
Two new research papers address the critical issue of AI hallucinations in different domains. One paper introduces ACL-Verbatim, an extractive question-answering system designed to provide hallucination-free answers fro…
-
Hugging Face releases open multilingual embedding models with 32K context
Hugging Face has released Granite Embedding Multilingual R2, a suite of open-source multilingual embedding models. The release includes a 97M-parameter compact model that leads in retrieval quality among open models und…
-
AI predicts human rater disagreement in LLM-generated difficulty scores
Researchers have developed a new method to predict when AI-generated difficulty ratings for educational materials might disagree with human assessments. This approach uses a separate embedding space, like ModernBERT, to…
-
IBM Granite releases two multilingual embedding models built on ModernBERT
IBM's Granite division has released two new multilingual embedding models, one with 97 million parameters and another with 311 million. These models are based on ModernBERT architecture and support over 200 languages, w…
-
AI models struggle with emotion nuance, researchers explore new evaluation and generation methods
Researchers are exploring the nuances of emotion in AI, with several papers focusing on Large Language Models (LLMs) and speech processing. One study investigates how well small language models preserve emotions during …