Subject
7 entries
Prompting
Bookmarks
Graph of Thoughts: Solving Elaborate Problems with LLMs
Graph of Thoughts (GoT) extends chain-of-thought and tree-of-thought prompting to arbitrary graph structures — letting LLM reasoning steps combine, branch, and loop rather than just proceeding linearly. More expressive than CoT or ToT for complex multi-step problems.
Self-Refine: Iterative LLM Output Improvement via Self-Feedback
Self-Refine is a framework where LLMs generate feedback on their own outputs and iteratively refine them — no human feedback, no gradient updates. Shows that a single LLM can be its own critic and improve outputs across diverse tasks.
Program of Thoughts Prompting: Disentangling Computation from Reasoning
Program of Thoughts separates reasoning from computation by having LLMs write executable Python programs rather than performing arithmetic inline, delegating number-crunching to an interpreter. It substantially outperforms chain-of-thought on numerical reasoning benchmarks by eliminating the arithmetic errors that plague prose reasoning chains.
Differentiable Prompt Makes Pre-trained Language Models Better Few-Shot Learners
DifferentiablePrompt (DPT) replaces discrete token prompts with optimized continuous embeddings, enabling gradient-based prompt tuning for few-shot learning. Published at ICLR 2022, it established that soft prompts can match full fine-tuning with far fewer parameters.
DART: Differentiable Prompt Makes Pre-Trained Language Models Better Few-Shot Learners
DART (Differentiable pRompT) trains prompt templates end-to-end via backpropagation, treating prompts as learnable continuous vectors rather than fixed text. It makes small pre-trained language models competitive few-shot learners without scaling to GPT-3 sizes — an important stepping stone between hand-crafted prompts and full fine-tuning.
The DALL-E 2 Prompt Book
The DALL-E 2 Prompt Book was an early community-produced guide to prompt engineering for image generation — cataloging styles, artists, modifiers, and composition techniques that reliably produce specific visual outputs. A snapshot of the craft before the field became saturated with guides.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
PromptSource is an IDE and community repository for creating, sharing, and iterating on natural language prompts that map dataset examples to input-output pairs for language model training and evaluation. With over 2,000 prompts for ~170 datasets, it provided the infrastructure behind the T0 family of models and multitask prompted training research.