在大型语言模型时代，对话分析的必要性：任务、技术和趋势调查

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends

September 21, 2024

作者: Xinghua Zhang, Haiyang Yu, Yongbin Li, Minzheng Wang, Longze Chen, Fei Huang

cs.AI

摘要

在大型语言模型（LLMs）时代，由于语言用户界面的快速发展趋势，将积累大量对话记录。对话分析（CA）致力于从对话数据中揭示和分析关键信息，简化手动流程，支持业务洞察和决策制定。CA需要提取可操作的见解并推动赋能的需求日益突出，吸引了广泛关注。然而，由于缺乏对CA的明确范围，导致各种技术的分散，使得形成系统化技术协同以赋能业务应用变得困难。本文对CA任务进行了彻底审查和系统化，总结了现有相关工作。具体而言，我们正式定义CA任务，以应对这一领域中碎片化和混乱的局面，并从对话场景重建、深入归因分析，到执行有针对性的训练，最终基于有针对性训练生成对话以实现特定目标，推导出CA的四个关键步骤。此外，我们展示了相关基准，讨论了潜在挑战，并指出了行业和学术界的未来方向。鉴于当前的进展，明显大部分工作仍集中在分析表面对话元素，这在研究和业务之间存在相当大的差距，而借助LLMs，最近的工作显示出研究因果关系和战略任务的趋势，这些任务复杂且高级。分析的经验和见解必将在针对对话记录的业务运营中具有更广泛的应用价值。

English

In the era of large language models (LLMs), a vast amount of conversation logs will be accumulated thanks to the rapid development trend of language UI. Conversation Analysis (CA) strives to uncover and analyze critical information from conversation data, streamlining manual processes and supporting business insights and decision-making. The need for CA to extract actionable insights and drive empowerment is becoming increasingly prominent and attracting widespread attention. However, the lack of a clear scope for CA leads to a dispersion of various techniques, making it difficult to form a systematic technical synergy to empower business applications. In this paper, we perform a thorough review and systematize CA task to summarize the existing related work. Specifically, we formally define CA task to confront the fragmented and chaotic landscape in this field, and derive four key steps of CA from conversation scene reconstruction, to in-depth attribution analysis, and then to performing targeted training, finally generating conversations based on the targeted training for achieving the specific goals. In addition, we showcase the relevant benchmarks, discuss potential challenges and point out future directions in both industry and academia. In view of current advancements, it is evident that the majority of efforts are still concentrated on the analysis of shallow conversation elements, which presents a considerable gap between the research and business, and with the assist of LLMs, recent work has shown a trend towards research on causality and strategic tasks which are sophisticated and high-level. The analyzed experiences and insights will inevitably have broader application value in business operations that target conversation logs.