Context-dependent Instruction Tuning for Dialogue Response Generation

TL;DR

This paper proposes a context-dependent instruction tuning method for multi-turn dialogue generation, where instructions are generated based on dialogue context to improve response quality and reduce computational costs.

Contribution

It introduces a novel framework that generates context-aware instructions for dialogue models, enhancing response accuracy in complex multi-turn conversations.

Findings

Achieves comparable or better results than baselines on dialogue benchmarks.

Reduces computational budget for training and inference.

Effectively aligns instructions with dialogue context during fine-tuning.

Abstract

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task instructions, many instruction datasets only provide a few instructions for the entire task, without considering the input of each example in the task. However, this approach becomes ineffective in complex multi-turn dialogue generation tasks, where the input varies highly with each turn as the dialogue context changes, so that simple task instructions cannot improve the generation performance. To address this limitation, we introduce a context-based instruction fine-tuning framework for each multi-turn dialogue which generates both responses and instructions based on the previous context as input. During the evaluation, the model generates instructions based on the previous context to self-guide the response. The proposed framework produces comparable or even outstanding results compared to the baselines by aligning instructions to the input during fine-tuning with the instructions in quantitative evaluations on dialogue benchmark datasets with reduced computation budget.