AI tricks

Prompt Engineering

• 2025-03: Prompting Science Report 1: Prompt Engineering is Complicated and Contingent
• 2024-06: The Prompt Report: A Systematic Survey of Prompting Techniques

In-Context Learning

• 2020-05: Language Models are Few-Shot Learners
• 2025-03: Learning to Search Effective Example Sequences for In-Context Learning

Chain of Thought (CoT)

"Let's think step-by-step"

• TextGrad: Automatic "Differentiation" via Text

Multi-step

Tool-use, feedback, agentic

• ReAct: Synergizing Reasoning and Acting in Language Models

Retrieval-Augmented Generation (RAG)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Input/Output Formats

• 2024-08: LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
• 2024-11: Does Prompt Formatting Have Any Impact on LLM Performance?

Position Bias

• 2023-07: Lost in the Middle: How Language Models Use Long Contexts
• Test models:
  • Needle-in-a-Haystack tests
  • 2023-08: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
  • 2024-02: ∞Bench: Extending Long Context Evaluation Beyond 100K Tokens
  • 2024-07: Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
• 2024-07: Eliminating Position Bias of Language Models: A Mechanistic Approach

Generation

• Large Language Models for Data Annotation and Synthesis: A Survey