Standard 4 stops to get here · leads to 3
Text Generation
Automatically creating coherent text using language models, from simple completion to creative writing.
Your route here
4 stops · basics first
- Natural Language Processing ✓ understood
The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.
- Token ✓ understood
The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.
- Tokenization ✓ understood
Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.
- Language Modeling ✓ understood
Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.
- Text Generation · you are here ✓ understood
Where it sits
Before this
Language Modeling Text Generation
Explore nearby
Language & LLMs Large Language Model A neural network, almost always a transformer, trained on vast amounts of text to predict the next token, which lets it write, answer, summarize and follow instructions. Language & LLMs Autoregressive Model A model that generates output one token at a time, using previously generated tokens as input for the next prediction. Language & LLMs Temperature A sampling parameter controlling randomness in generation - lower values make output more deterministic, higher more creative. Language & LLMs Top-p Sampling Nucleus sampling - selecting from the smallest set of tokens whose cumulative probability exceeds p, providing dynamic vocabulary. Language & LLMs Greedy Decoding Always selecting the most likely next token during generation, fast but can lead to repetitive or suboptimal outputs. Language & LLMs GPT Generative Pre-trained Transformer - an autoregressive language model architecture that predicts the next token given previous context.