From Instruction to Output: The Role of Prompting in Modern NLG

ACL ARR 2025 July Submission156 Authors

Abstract:

Prompt engineering has emerged as an integral technique for
extending the strengths and abilities of Large Language Models
(LLMs) to gain significant performance gains in various Natural
Language Processing (NLP) tasks. This approach, which requires
instructions to be composed in natural language to bring out
the knowledge from LLMs in a structured way, has driven
breakthroughs in various NLP tasks. Yet, there is still no
structured framework or coherent understanding of the varied
prompt‐engineering methods and techniques, particularly in
the field of Natural Language Generation (NLG).

This brief survey aims to help fill that gap by outlining
recent developments in prompt engineering,
and their effect on different NLG tasks. We also
position prompt design as an input-level control mechanism for
NLG outputs, contrasting it with fine-tuning.

Paper Type: Short

Research Area: Language Modeling

Research Area Keywords: prompting, applications, LLM/AI agents

Contribution Types: Surveys, Theory

Languages Studied: English

Submission Number: 156