Instruction Tuning for Story Understanding and Generation with Weak Supervision

TL;DR

This paper introduces Weak to Strong Instruction Tuning, a method that enhances large language models' ability to understand and generate stories by training with instructions of varying clarity, leading to improved narrative quality.

Contribution

The paper presents a novel instruction tuning approach that significantly improves story understanding and generation in large language models by leveraging weak and strong instructions.

Findings

Outperforms state-of-the-art baselines in benchmark datasets

Improves automatic evaluation metrics for story tasks

Enhances human judgment of narrative coherence

Abstract

Story understanding and generation have long been a challenging task in natural language processing (NLP), especially when dealing with various levels of instruction specificity. In this paper, we propose a novel approach called "Weak to Strong Instruction Tuning" for improving story generation by tuning models with instructions of varying clarity. We explore the potential of large language models (LLMs) to adapt to different types of instructions, weak and strong, and show that our method significantly enhances performance in story comprehension and generation. By leveraging the strength of instruction tuning, we train models to understand the nuances of story plots, characters, and themes while generating coherent and engaging narratives. Through extensive experiments on several benchmark datasets and comparison with state-of-the-art baselines, we demonstrate that our method outperforms existing techniques, yielding substantial improvements in both automatic evaluation metrics and human evaluations. Our work shows that adaptive instruction tuning can be a powerful tool in refining generative models for complex narrative tasks.