Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method

Joshua Zingale, Jugal Kalita


Abstract
Controlled text generation (CTG) seeks to guide large language model (LLM) output, that statistical language generation would conform to desired criteria. The current study presents a novel CTG algorithm that enforces adherence toward specific rhetorical relations in an LLM sentence-completion context by a parser-driven decoding scheme that requires no model fine-tuning. The method is validated both with automatic and human evaluation.
Anthology ID:
2024.eacl-short.18
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
193–203
Language:
URL:
https://aclanthology.org/2024.eacl-short.18
DOI:
Bibkey:
Cite (ACL):
Joshua Zingale and Jugal Kalita. 2024. Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 193–203, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method (Zingale & Kalita, EACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eacl-short.18.pdf
Video:
 https://aclanthology.org/2024.eacl-short.18.mp4