AutoHint: Automatic Prompt Optimization with Hint Generation
This work addresses the challenge of developing high-quality prompts for LLMs in specific tasks, offering an incremental improvement over existing methods.
The paper tackles the problem of automatic prompt engineering for Large Language Models by introducing AutoHint, a framework that generates enriched instructions from labeled data to optimize prompts, resulting in significant accuracy improvements on the BIG-Bench Instruction Induction dataset for zero-shot and few-shot tasks.
This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the key to applying this ability to specific tasks lies in developing high-quality prompts. Thus we propose a framework to inherit the merits of both in-context learning and zero-shot learning by incorporating enriched instructions derived from input-output demonstrations to optimize original prompt. We refer to the enrichment as the hint and propose a framework to automatically generate the hint from labeled data. More concretely, starting from an initial prompt, our method first instructs a LLM to deduce new hints for selected samples from incorrect predictions, and then summarizes from per-sample hints and adds the results back to the initial prompt to form a new, enriched instruction. The proposed method is evaluated on the BIG-Bench Instruction Induction dataset for both zero-shot and few-short prompts, where experiments demonstrate our method is able to significantly boost accuracy for multiple tasks.