Сравнение на методи

	Commonsense Reasoning	Генериране с разширение за извличане (Retrieval-Augmented Generation, RAG)
Област	Извличане на текст	Извличане на текст
Семейство	Process / pipeline	Process / pipeline
Година на възникване	2019 (landmark benchmarks)	2020
Създател	Sap et al. (ATOMIC, 2019); Zellers et al. (HellaSwag, 2019)	Lewis, Patrick et al. (Meta AI / Facebook AI Research)
Тип	NLP reasoning task	Hybrid retrieval + generation pipeline
Основополагащ източник	Sap, M. et al. (2019). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI.	Lewis, P. et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS), 33, 9459-9474.
Други названия	commonsense NLP, if-then reasoning, Sağduyu Akıl Yürütme (Commonsense Reasoning)	RAG, retrieval-augmented LLM, grounded generation, Erişim Destekli Metin Üretimi (RAG)
Свързани	6	7
Резюме	Commonsense reasoning in NLP refers to the capacity of a language model or inference system to draw on implicit, world-knowledge facts that humans take for granted — facts not stated in the text — to answer questions, complete stories, or interpret dialogue. Landmark benchmarks formalising the task include ATOMIC (Sap et al., 2019), an if-then commonsense knowledge graph, and HellaSwag (Zellers et al., 2019), a sentence-completion challenge that exposed gaps in machine understanding of everyday events.	Retrieval-Augmented Generation (RAG) is a natural-language-processing pipeline introduced by Lewis et al. in 2020 that strengthens a large language model (LLM) with evidence fetched at inference time from an external knowledge base. Instead of relying solely on what a model memorised during training, RAG first retrieves the most relevant passages from a document index and then hands those passages to the LLM as context, grounding the generated answer in verifiable, up-to-date information. The approach reduces hallucination and allows domain-specific or time-sensitive knowledge to be injected without retraining the model.