Chain-of-Interactions: Multi-step Iterative ICL Framework for Abstractive Task-Oriented Dialogue Summarization of Conversational AI Interactions

Large Language Models (LLMs) have introduced paradigm-shifting approaches in natural language processing. Yet, their transformative in-context learning (ICL) capabilities remain underutilized, especially in customer service dialogue summarization-a domain plagued by generative hallucinations, detail omission, and inconsistencies. We present Chain-of-Interactions (CoI), a novel singleinstance, multi-step framework that orchestrates information extraction, self-correction, and evaluation through sequential interactive generation chains. By strategically leveraging LLMs' ICL capabilities through precisely engineered prompts, CoI dramatically enhances abstractive task-oriented dialogue summarization (ATODS) quality and usefulness. Our comprehensive evaluation on real-world and benchmark human-agent interaction datasets demonstrates CoI's effectiveness through rigorous testing across 11 models and 7 prompting approaches, with 9 standard automatic evaluation metrics, 3 LLM-based evaluations, and human studies involving 480 evaluators across 9 quality dimensions. Results reveal CoI's decisive superiority, outperforming all singlestep approaches and achieving 6× better entity preservation, 49% higher quality scores, and 322% improvement in accuracy compared to state-of-the-art multi-step Chain-of-Density (CoD). This research addresses critical gaps in task-oriented dialogue summarization for customer service applications and establishes new standards for harnessing LLMs' reasoning capabilities in practical, industry-relevant contexts 1 .