Saved in:
Bibliographic Details
Main Authors: Chowdhury, Faisal, Mihindukulasooriya, Nandana, D'Souza, Niharika S, Samulowitz, Horst, Gupta, Neeru, Hanusiak, Tomasz, Kapitonow, Michal
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.03130
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909982697455616
author Chowdhury, Faisal
Mihindukulasooriya, Nandana
D'Souza, Niharika S
Samulowitz, Horst
Gupta, Neeru
Hanusiak, Tomasz
Kapitonow, Michal
author_facet Chowdhury, Faisal
Mihindukulasooriya, Nandana
D'Souza, Niharika S
Samulowitz, Horst
Gupta, Neeru
Hanusiak, Tomasz
Kapitonow, Michal
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03130
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic Prompt Engineering with No Task Cues and No Tuning
Chowdhury, Faisal
Mihindukulasooriya, Nandana
D'Souza, Niharika S
Samulowitz, Horst
Gupta, Neeru
Hanusiak, Tomasz
Kapitonow, Michal
Artificial Intelligence
Computation and Language
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.
title Automatic Prompt Engineering with No Task Cues and No Tuning
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2601.03130