Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
This addresses a challenge in task-oriented dialogue systems for users needing reliable AI assistance, though it is incremental as it builds on existing prompting methods.
The paper tackles the problem of large language models struggling with complex multi-turn dialogue contexts by proposing a Self-Explanation prompting strategy, which improves performance across six benchmark datasets, matching or exceeding few-shot prompts.
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts. In this study, we propose a novel "Self-Explanation" prompting strategy to enhance the comprehension abilities of LLMs in multi-turn dialogues. This task-agnostic approach requires the model to analyze each dialogue utterance before task execution, thereby improving performance across various dialogue-centric tasks. Experimental results from six benchmark datasets confirm that our method consistently outperforms other zero-shot prompts and matches or exceeds the efficacy of few-shot prompts, demonstrating its potential as a powerful tool in enhancing LLMs' comprehension in complex dialogue tasks.