Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tam, Zhi Rui, Wu, Cheng-Kuang, Tsai, Yi-Lin, Lin, Chieh-Yen, Lee, Hung-yi, Chen, Yun-Nung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917801678077952
author Tam, Zhi Rui
Wu, Cheng-Kuang
Tsai, Yi-Lin
Lin, Chieh-Yen
Lee, Hung-yi
Chen, Yun-Nung
author_facet Tam, Zhi Rui
Wu, Cheng-Kuang
Tsai, Yi-Lin
Lin, Chieh-Yen
Lee, Hung-yi
Chen, Yun-Nung
contents Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information from large language models (LLMs). This study investigates whether such constraints on generation space impact LLMs abilities, including reasoning and domain knowledge comprehension. Specifically, we evaluate LLMs performance when restricted to adhere to structured formats versus generating free-form responses across various common tasks. Surprisingly, we observe a significant decline in LLMs reasoning abilities under format restrictions. Furthermore, we find that stricter format constraints generally lead to greater performance degradation in reasoning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
Tam, Zhi Rui
Wu, Cheng-Kuang
Tsai, Yi-Lin
Lin, Chieh-Yen
Lee, Hung-yi
Chen, Yun-Nung
Computation and Language
Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information from large language models (LLMs). This study investigates whether such constraints on generation space impact LLMs abilities, including reasoning and domain knowledge comprehension. Specifically, we evaluate LLMs performance when restricted to adhere to structured formats versus generating free-form responses across various common tasks. Surprisingly, we observe a significant decline in LLMs reasoning abilities under format restrictions. Furthermore, we find that stricter format constraints generally lead to greater performance degradation in reasoning tasks.
title Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2408.02442