Factored Cognition Primer - Primer
primer.ought.org · 132 words · saved by 2 readers
How to write compositional language model programs
⌘Ctrlk Factored Cognition Primer How to write compositional language model programs You’ll learn how to: Amplify language models like GPT-3 through recursive question-answering and debate Reason about long texts by combining search and generation Run decompositions quickly by parallelizing language model calls Build human-in-the-loop agents Use verification of answers and reasoning steps to improve responses And more! The book focuses on techniques that are likely to remain relevant for better language models. How to cite this book Please cite this book as: BibTeX: Last updated…
saved by
related reading
- Recursive Language Models | Alex L. Zhangalexzhang13.github.io
- GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
- Language Models can Solve Computer Tasksarxiv.org
- Prime Agent: A Self-Improving RLM Harnessarxiv.org
- [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
- Thinking to recall: How reasoning unlocks parametric knowledge in LLMsresearch.google
- [2203.14465] STaR: Bootstrapping Reasoning With Reasoningarxiv.org
- Language Model Compositionarxiv.org
- [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
- Recursively Summarizing Booksarxiv.org