Content deleted Content added
m Merge |
|||
Line 1:
{{Short description|Language models designed for reasoning tasks}}{{Merge to|Reflection (artificial intelligence)|date=April 2025}}{{unreliable sources|date=January 2025}}
'''Reasoning language models''' are [[artificial intelligence]] systems that combine [[natural language processing]] with structured reasoning capabilities. These models are usually constructed by [[Prompt engineering|prompting]], [[Fine-tuning (deep learning)|supervised finetuning]] (SFT), and [[reinforcement learning]] (RL) initialized with [[Pretrained language model|pretrained language models]].
Line 7 ⟶ 5:
== Prompting ==
{{Main|Prompt engineering}}
A language model is a generative model of a training dataset of texts. Prompting means constructing a text prompt, such that, conditional on the text prompt, the language model generates a solution to the task. Prompting can be applied to a pretrained model ("base model"), a base model that has undergone SFT, or RL, or both.<ref>{{Citation |last1=Qiao |first1=Shuofei |title=Reasoning with Language Model Prompting: A Survey |date=2023-09-18 |arxiv=2212.09597 |last2=Ou |first2=Yixin |last3=Zhang |first3=Ningyu |last4=Chen |first4=Xiang |last5=Yao |first5=Yunzhi |last6=Deng |first6=Shumin |last7=Tan |first7=Chuanqi |last8=Huang |first8=Fei |last9=Chen |first9=Huajun}}</ref>
| |||