#Prompting
- System prompts
- Source: Zheng et al. 2023: Step-Back Prompting
- Source: XGrammar (GitHub README and docs)
- Source: vLLM Structured Outputs Docs
- Source: Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Source: The Instruction Hierarchy (OpenAI)
- Source: Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Source: Say What You Mean (.txt response to Let Me Speak Freely)
- Source: Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
- Source: Reduce hallucinations (Claude Docs)
- Source: Reasoning models don't always say what they think (Anthropic)
- Source: Reasoning best practices (OpenAI)
- Source: Prompting Science Report 2: The Decreasing Value of Chain of Thought
- Source: Prompting best practices (Anthropic)
- Source: Prompt engineering overview (Anthropic)
- Source: Prompt engineering guide (OpenAI)
- Source: Prompt design strategies (Google Gemini)
- Source: Prompt & Context Engineering (Notebook tutorial)
- Source: Press et al. 2022: Self-Ask (Measuring and Narrowing the Compositionality Gap)
- Source: Outlines Documentation and README
- Source: Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs (MIPRO, 2024)
- Source: OpenAI Model Spec (2026-10-29)
- Source: Notebook experiment 17-tree-of-thoughts (Tree of Thoughts)
- Source: Notebook experiment 16-self-consistency (Self-Consistency)
- Source: Notebook experiment 15-chain-of-thought (Chain-of-Thought)
- Source: Mid-conversation system messages (Anthropic)
- Source: Long context prompting for Claude 2.1 (Anthropic)
- Source: LLGuidance: Making Structured Outputs Go Brrr
- Source: llguidance (GitHub README)
- Source: Large Language Models are Zero-Shot Reasoners
- Source: Language Models Don't Always Say What They Think
- Source: Language Models are Few-Shot Learners (GPT-3)
- Source: JSONSchemaBench (Generating Structured Outputs from Language Models)
- Source: Instructor Documentation and README
- Source: Guiding LLMs The Right Way (DOMINO)
- Source: GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning (Agrawal et al., 2025)
- Source: DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (Khattab et al., 2023)
- Source: DSPy documentation (signatures, modules, adapters, optimizers)
- Source: DSPy 3.5 release notes
- Source: DIN-SQL (Pourreza and Rafiei, NeurIPS 2023)
- Source: Chain-of-Verification Reduces Hallucination in Large Language Models (Meta, 2023)
- Source: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Source: Calibrate Before Use: Improving Few-Shot Performance of Language Models
- Query Transformation
- Prompt engineering
- Instructor and Outlines
- Few-shot prompting
- DSPy
- Constrained Decoding
- Chain-of-thought