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

Autor:	Zingale, Joshua, Kalita, Jugal
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Controlled text generation (CTG) seeks to guide large language model (LLM) output to produce text that conforms 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. The code is accessible on GitHub. Comment: To be published in the main proceedings of the Association for Computational Linguistics, European Chapter (EACL 2024)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.06125 Zobrazit plný text záznamu View this record from Arxiv