Tag: small language models
Browse our exclusive articles!
Zero-Shot Confidence Estimation for Small LLMs Explained
Discover how zero-shot confidence estimation outperforms supervised baselines in small LLMs, boosting accuracy and reducing latency without extra training.
Evaluating Small Language Models for Multi-Turn Customer QA
Explore how small language models perform in context-aware, multi-turn customer-service QA compared to large models using synthetic data.
RadLite: Efficient CPU Radiology AI with LoRA Fine-Tuning
RadLite uses LoRA fine-tuning on small language models for multi-task radiology AI, enabling CPU deployment and high accuracy in clinical settings.
RSAT: Boosting Small Language Models for Accurate Table Reasoning
Discover how RSAT improves faithfulness and transparency in small language models for reliable table reasoning with structured attribution.
Preserving Emotion in Small Model Machine Translation
Explore how small language models preserve fine-grained emotions in machine translation using emotion-aware prompting and ModernBERT evaluation.