Architettura transformer per LLM, positional encoding, hallucination, scaling laws, benchmarking e teoria avanzata sui modelli linguistici.
- Architettura transformer per LLM
- Positional encoding (RoPE, ALiBi)
- Hallucination: cause, rilevamento e mitigazione
- Scaling laws e crescita degli LLM
- Chain-of-thought e few-shot prompting
- Benchmarking e valutazione degli LLM
- Understanding the Transformer Architecture of Large Language Models.md
- Hallucination in Language Models Critical Considerations.md
- Chain-of-Thought Prompting for Reasoning in Large Language Models.md
- The Exponential Growth of Large Language Models.md
- Evaluating Large Language Models 30 Common Metrics.md
- Strategies for Mitigating AI Hallucinations.md