LLM Prompting

LLM: Large Language Model

Overview

The field studies how the wording and structure of inputs affect what language models understand, generate, and reliably follow. Common approaches include zero- and few-shot in-context learning, chain-of-thought and task decomposition, retrieval-augmented context, and structured prompts using schemas, roles, or constraints. Researchers also develop automated prompt search, feedback-driven refinement, and methods that adapt examples or context to each input, testing them on tasks such as reasoning, classification, code generation, and information extraction. Prompting can improve performance without changing model weights, but its effects vary across models and tasks: added instructions can hurt, and gains in accuracy may trade off with reliability, diversity, safety, or cost.

Latest papers

CardsList

452 papers23 papers in the last four weeks, down 41% on the four weeks before. 0.2% of all new papers.

  1. Budgeted Prompt-Set Expansion and Refinement for Language Models via Simulation Optimization

    Apr 12, 2024Haoting Zhang, Jinghai He, Rhonda Righter +1Prompt OptimizationLLM Prompting

  2. An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models

    Apr 3, 2024Emmy Liu, Graham Neubig, Jacob AndreasDeductive Reasoning in Language ModelsLLM Prompting