Modifying large language model post-training for diverse creative writing

Abstract

As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. However, LLM post-training often focuses on improving generation quality but neglects to facilitate output diversity. Hence, in creative writing generation, we investigate post-training approaches to promote both output diversity and quality. Our core idea is to include deviation – the degree of difference between a trainin

Relevance Assessment

Research Gap

Notes are automatically saved as you type

Search Queries