Tag: AI language models
Browse our exclusive articles!
SHIELD Dataset & Models for Clinical Note De-identification
Discover SHIELD, a diverse clinical note dataset and distilled language models for efficient, enterprise-scale de-identification of sensitive health data.
Self-Mined Hardness: Boosting AI Safety Fine-Tuning
Discover how self-mined hardness improves AI safety by reducing jailbreak attacks and balancing refusal rates in language models.
Enhancing Multilingual AI Safety with Self-Distillation
Discover how self-distillation improves safety alignment in multilingual AI, boosting protection in low-resource languages without extensive data.
EvoLM: Self-Evolving Language Models Without Supervision
Discover EvoLM, a self-evolving language model that improves autonomously using co-evolved discriminative rubrics, outperforming GPT-4.1 on benchmarks.
H-Probes: Revealing Hierarchical Structures in Language Models
Discover how H-probes extract hierarchical structures from language model representations to boost AI interpretability and reasoning performance.