Automatic Prompt Engineering with No Task Cues and No Tuning

2026-01-06

arXiv.org

AI Summary

This study addresses the challenge of automatically generating effective prompts without explicit task instructions or model fine-tuning, focusing on the underexplored task of cryptic column name expansion (CNE) in database tables. The authors propose a minimalist approach to automatic prompt engineering that integrates zero-shot reasoning with off-the-shelf large language models, enabling cross-lingual prompt construction even in the complete absence of explicit task cues. To the best of our knowledge, this work is the first to apply automatic prompt engineering to CNE and demonstrates its effectiveness in non-English contexts, particularly German. Experimental results show that the method achieves performance on par with existing, more complex approaches on English–German bilingual datasets, offering a novel paradigm for table understanding and search.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This paper presents a system for automatic prompt engineering that is much simpler in both design and application and yet as effective as the existing approaches. It requires no tuning and no explicit clues about the task. We evaluated our approach on cryptic column name expansion (CNE) in database tables, a task which is critical for tabular data search, access, and understanding and yet there has been very little existing work. We evaluated on datasets in two languages, English and German. This is the first work to report on the application of automatic prompt engineering for the CNE task. To the best of our knowledge, this is also the first work on the application of automatic prompt engineering for a language other than English.

Problem

• automatic prompt engineering
• cryptic column name expansion
• tabular data understanding
• zero-shot prompting
• multilingual prompting

Innovation

• automatic prompt engineering
• no tuning
• no task cues
• cryptic column name expansion
• multilingual prompting