Tag: natural language processing
Browse our exclusive articles!
mSFT: Efficient Multi-task SFT to Prevent Overfitting
Discover mSFT, a novel multi-task SFT method that reduces overfitting and boosts NLP model performance with adaptive dataset training.
ProFit: Enhancing SFT with Probability-Guided Token Selection
Discover ProFit, a novel method improving Supervised Fine-Tuning by masking low-probability tokens to boost LLM alignment and reasoning performance.
Evaluating Large Language Models with Coupled Token Generation
Discover how coupled token generation improves evaluation accuracy and reduces sample needs in large language model assessments.
Ukrainian Visual Word Sense Disambiguation Benchmark Study
Explore the new Ukrainian Visual Word Sense Disambiguation benchmark assessing NLP models on ambiguous word-image matching tasks.
Gemini 3.1 Flash Live: Enhancing Natural Audio AI
Discover how Gemini 3.1 Flash Live improves audio AI with natural voice recognition, real-time processing, and reliable speech synthesis across industries.