Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method
This addresses the challenge of controlled text generation for users needing structured outputs, but it is incremental as it builds on existing CTG methods.
The paper tackles the problem of guiding large language model sentence completion to adhere to specific rhetorical relations, presenting a parser-driven decoding scheme that achieves this without fine-tuning, validated through automatic and human evaluation.
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.