Does Prompt Formatting Have Any Impact on LLM Performance?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Jia, Rungta, Mukund, Koleczek, David, Sekhon, Arshdeep, Wang, Franklin X, Hasan, Sadid
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917839334539264
author He, Jia
Rungta, Mukund
Koleczek, David
Sekhon, Arshdeep
Wang, Franklin X
Hasan, Sadid
author_facet He, Jia
Rungta, Mukund
Koleczek, David
Sekhon, Arshdeep
Wang, Franklin X
Hasan, Sadid
contents In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. Although previous research has explored aspects like rephrasing prompt contexts, using various prompting techniques (like in-context learning and chain-of-thought), and ordering few-shot examples, our understanding of LLM sensitivity to prompt templates remains limited. Therefore, this paper examines the impact of different prompt templates on LLM performance. We formatted the same contexts into various human-readable templates, including plain text, Markdown, JSON, and YAML, and evaluated their impact across tasks like natural language reasoning, code generation, and translation using OpenAI's GPT models. Experiments show that GPT-3.5-turbo's performance varies by up to 40\% in a code translation task depending on the prompt template, while larger models like GPT-4 are more robust to these variations. Our analysis highlights the need to reconsider the use of fixed prompt templates, as different formats can significantly affect model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10541
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Does Prompt Formatting Have Any Impact on LLM Performance?
He, Jia
Rungta, Mukund
Koleczek, David
Sekhon, Arshdeep
Wang, Franklin X
Hasan, Sadid
Computation and Language
Machine Learning
In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. Although previous research has explored aspects like rephrasing prompt contexts, using various prompting techniques (like in-context learning and chain-of-thought), and ordering few-shot examples, our understanding of LLM sensitivity to prompt templates remains limited. Therefore, this paper examines the impact of different prompt templates on LLM performance. We formatted the same contexts into various human-readable templates, including plain text, Markdown, JSON, and YAML, and evaluated their impact across tasks like natural language reasoning, code generation, and translation using OpenAI's GPT models. Experiments show that GPT-3.5-turbo's performance varies by up to 40\% in a code translation task depending on the prompt template, while larger models like GPT-4 are more robust to these variations. Our analysis highlights the need to reconsider the use of fixed prompt templates, as different formats can significantly affect model performance.
title Does Prompt Formatting Have Any Impact on LLM Performance?
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.10541