边聊边生成摘要，智能降负提效率。
Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback
- 对话中实时生成简要笔记，避免重复回顾。
- 比批量总结快3%（复杂案可快9%），且满意度高。
- 支持持续优化，适合客服场景规模化使用。
我们提出一种面向客服的增量式摘要系统，通过细调Mixtral-8x7B模型实现对话中连续生成笔记，并用DeBERTa分类器过滤无关内容。客服编辑实时反馈用于在线笔记更新与离线模型再训练，形成闭环。部署后，相比批量摘要，案例处理时间平均减少3%（复杂案例最高达9%），问卷调查显示客服满意度高。结果表明，结合持续反馈的增量摘要能有效提升摘要质量与客服工作效率。
原文摘要 · Abstract (English)
We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agents' context-switching effort and redundant review. Our approach combines a fine-tuned Mixtral-8x7B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. Agent edits refine the online notes generation and regularly inform offline model retraining, closing the agent edits feedback loop. Deployed in production, our system achieved a 3% reduction in case handling time compared to bulk summarization (with reductions of up to 9% in highly complex cases), alongside high agent satisfaction ratings from surveys. These results demonstrate that incremental summarization with continuous feedback effectively enhances summary quality and agent productivity at scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。