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

Code

• github.com/joshua-zingale/plug-and-play-rst-ctg
  OfficialIn paperpytorch★ 1

Abstract

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.

Tasks

Reproductions