Let Me Speak Freely? A Study On The Impact Of Format Restrictions On Large Language Model Performance.
Zhi Rui Tam, Cheng-Kuang Wu, Yi-Lin Tsai, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen
Abstract
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.
BibTeX
@inproceedings{tam-etal-2024-speak,
title = "Let Me Speak Freely? A Study On The Impact Of Format Restrictions On Large Language Model Performance.",
author = "Tam, Zhi Rui and
Wu, Cheng-Kuang and
Tsai, Yi-Lin and
Lin, Chieh-Yen and
Lee, Hung-yi and
Chen, Yun-Nung",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.91/",
doi = "10.18653/v1/2024.emnlp-industry.91",
pages = "1218--1236"
}