GLiNER2
PulseAugur coverage of GLiNER2 — every cluster mentioning GLiNER2 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New multilingual privacy tagger outperforms GLiNER2, Presidio, and OpenAI
Researchers have developed a new multilingual named-entity tagger designed for privacy redaction, outperforming existing tools like GLiNER2, Microsoft Presidio, and OpenAI Privacy Filter. This tagger, fine-tuned on a mu…
-
Fastino releases GLiNER2.5 with boundary prediction for efficient information extraction
Fastino has released GLiNER2.5, an information extraction model that replaces span enumeration with boundary prediction. This architectural change allows for longer context windows up to 4,096 words and linear computati…
-
New Opir models offer efficient multi-task safety classification for LLMs
Researchers have introduced Opir, a new family of encoder-based guardrail models designed for efficient multi-task safety classification in large language model applications. Opir models are built on the GLiClass archit…
-
GLiNER Guard unifies LLM safety and PII detection in single pass
A new system called GLiNER Guard (GLiGuard) has been developed to streamline safety moderation and PII detection for large language models. This unified encoder collapses multiple classifiers and NER models into a singl…
-
New GLiNER2-PII model excels at multilingual PII extraction
Researchers have developed GLiNER2-PII, a compact 0.3 billion parameter model designed for multilingual personally identifiable information (PII) extraction. This model, adapted from GLiNER2, can identify 42 different t…