Uporedite metode

	Инжењеринг упутстава	LoRA i PEFT
Oblast	Rudarenje teksta	Duboko učenje
Porodica	Process / pipeline	Machine learning
Godina nastanka	2020 (few-shot prompting); 2022 (chain-of-thought)	2022
Tvorac	Tom Brown et al. (GPT-3 / few-shot framing, 2020); chain-of-thought extended by Jason Wei et al. (2022)	Hu, E. J. et al.; Lester, B. et al.
Tip	NLP pipeline — structured instruction design for large language models	Parameter-efficient fine-tuning of large pretrained models
Temeljni izvor	Brown, T. et al. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems (NeurIPS), 33, 1877-1901.	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.
Drugi nazivi	instruction design, LLM prompting, Yönerge Mühendisliği (Prompt Engineering)	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning
Srodne	7	5
Sažetak	Prompt engineering is the practice of crafting structured natural-language instructions — prompts — to elicit targeted outputs from large language models (LLMs). Formalised by Brown et al. (2020) in the context of GPT-3 and extended by Wei et al. (2022) with chain-of-thought prompting, it encompasses four main strategies: zero-shot, few-shot, chain-of-thought, and tree-of-thought. Rather than re-training a model, the analyst shapes the model's behaviour entirely through the design of the input text.	LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.