Effect of Selection Format on LLM Performance

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Han, Yuchen, Wu, Yucheng, Willard, Jeffrey
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909651185958912
author Han, Yuchen
Wu, Yucheng
Willard, Jeffrey
author_facet Han, Yuchen
Wu, Yucheng
Willard, Jeffrey
contents This paper investigates a critical aspect of large language model (LLM) performance: the optimal formatting of classification task options in prompts. Through an extensive experimental study, we compared two selection formats -- bullet points and plain English -- to determine their impact on model performance. Our findings suggest that presenting options via bullet points generally yields better results, although there are some exceptions. Furthermore, our research highlights the need for continued exploration of option formatting to drive further improvements in model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Effect of Selection Format on LLM Performance
Han, Yuchen
Wu, Yucheng
Willard, Jeffrey
Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
Emerging Technologies
Machine Learning
This paper investigates a critical aspect of large language model (LLM) performance: the optimal formatting of classification task options in prompts. Through an extensive experimental study, we compared two selection formats -- bullet points and plain English -- to determine their impact on model performance. Our findings suggest that presenting options via bullet points generally yields better results, although there are some exceptions. Furthermore, our research highlights the need for continued exploration of option formatting to drive further improvements in model performance.
title Effect of Selection Format on LLM Performance
topic Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2503.06926