Porównaj metody

	Mechanizm uwagi	Dostrajanie BERT	Dostrajanie GPT
Dziedzina	Uczenie głębokie	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning	Machine learning
Rok powstania	2015	2019	2019
Twórca	Bahdanau, D.; Luong, M.T.	Devlin, J. et al.	Radford, A. et al. (OpenAI)
Typ	Neural attention layer (encoder-decoder)	Transfer learning (fine-tuning a pre-trained transformer)	Fine-tuning of pretrained autoregressive language models
Źródło pierwotne	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL.	Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. & Sutskever, I. (2019). Language Models are Unsupervised Multitask Learners. OpenAI Technical Report.
Inne nazwy	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT	GPT İnce Ayar ve Talimat Uyarlaması, GPT fine-tuning, instruction tuning, LLM fine-tuning
Pokrewne	5	5	5
Podsumowanie	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.	BERT fine-tuning, building on the BERT model introduced by Devlin and colleagues in 2019, re-trains a pre-trained BERT model on a small labelled dataset for a target task such as classification, named-entity recognition, or question answering. Through transfer learning it reaches high performance even with relatively little task-specific data.	GPT fine-tuning adapts pretrained autoregressive language models such as GPT-2/3/4 or LLaMA — introduced in OpenAI's 2019 work by Radford and colleagues — to domain-specific data or to instruction following via reinforcement learning from human feedback (RLHF) or DPO. It is used for instruction following, domain adaptation, and generative tasks.