2023/09/22 by Haoyu Gao, Gao, Haoyu, Ting-En Lin +11 · 1 voice · 4 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2309.12940
openalex publication_date 2023/09/22 · arxiv published 2023/09/22 · arxiv updated 2023/09/22 · openalex created_date 2023/09/26 · openalex updated_date 2026/07/28
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.