From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

Ali Malik, Stephen Mayhew, Christopher Piech, Klinton Bicknell


Abstract
We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we evaluate the effectiveness of several key approaches for this task, including few-shot prompting, supervised finetuning, and reinforcement learning (RL), utilising both GPT-4 and open source alternatives like LLama2-7B and Mistral-7B.Our findings reveal a large performance gap between GPT-4 and the open source models when using prompt-based strategies. However, we show how to bridge this gap with a careful combination of finetuning and RL alignment. Our best model, CALM (CEFR-Aligned Language Model), surpasses the performance of GPT-4 and other strategies, at only a fraction of the cost. We further validate the quality of our results through a small-scale human study.
Anthology ID:
2024.findings-acl.926
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15670–15693
Language:
URL:
https://aclanthology.org/2024.findings-acl.926
DOI:
10.18653/v1/2024.findings-acl.926
Bibkey:
Cite (ACL):
Ali Malik, Stephen Mayhew, Christopher Piech, and Klinton Bicknell. 2024. From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 15670–15693, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation (Malik et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.926.pdf