ner

OpenMed 3.0 发布：基于 Apache-2.0 许可的临床 AI SDK，完全在本地运行、绝不回退到云端，可将临床文本转化为结构化且去标识化的洞察。

GLiNER2.5 is a multilingual boundary checkpoint for unified schema-based information extraction, supporting entities, classification, structured records, relations, and span attributes in one model.

Proposes FSE, a Fast-Slow Experts span-based NER model for continual learning, achieving state-of-the-art performance on CLNER benchmarks.

RuleChef is a framework that uses LLMs to generate human-editable, executable rules for NLP tasks, iteratively improving them based on examples and human feedback, resulting in fast, deterministic, and inspectable rule systems.

This paper characterizes when conformal risk control can certify structured LLM outputs, proving impossibility bounds and analyzing certification hierarchies across different bounds. Empirical validation on six open-weight models shows that hard configurations are uncertifiable at low risk levels but practical certification is achievable at relaxed targets.

This paper introduces BERTomelo, a next-generation monolingual encoder pre-trained for Portuguese using the ModernBERT architecture, achieving superior performance on downstream tasks like STS and NER compared to previous Portuguese and multilingual models.

BCL is the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations for information extraction tasks, showing consistent improvements over existing methods.

GLiNER-Relex is a unified framework for joint named entity recognition and relation extraction that leverages a shared transformer encoder for zero-shot capabilities. The paper demonstrates competitive performance on standard benchmarks and releases the model as an open-source Python package.