打造能卖货的智能主播，让AI说话更懂销售、更会打动观众。
VerbalValue: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce
- 构建产品知识库与销售术语词典，确保回答有据可依。
- 在1475段直播互动数据上微调模型，提升说服力和情感回应。
- 适合需要高转化率直播带货的电商场景，尤其看重真实感和互动性。
一位优秀的直播带货主播不仅是解说者，更是促成购买决策的销售员，通过专业产品知识、情感化应答策略及娱乐化内容实现商品曝光转化。然而现有AI系统难以复制此能力：对话推荐系统将推荐视为终点，通用大模型则编造产品信息，依赖通用话术，缺乏吸引力与说服力。我们提出VerbalValue，一个以销售转化为导向的虚拟主播，具备卓越语言表达能力并创造真实商业价值，主要贡献包括：首先，构建涵盖产品规格与精选销售术语的知识库，确保回答基于可靠专业知识；其次，收集并标注了1,475个涵盖多样化观众意图的直播互动样本；第三，基于该数据微调大语言模型，生成兼具同理心、商业导向的回应，通过情感强化、证据支撑反驳及幽默化解等策略适配不同观众意图。实验表明，相比GPT-5.4、Claude Sonnet 4.6、Gemini 3.1 Pro等基线模型，其信息量提升23%，事实正确率提高18%，并在得体性与观众参与度方面持续领先。
原文摘要 · Abstract (English)
A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionally intelligent response tactics, and entertainment that serves as a vehicle for product exposure. Yet no existing AI system replicates this: conversational recommenders treat recommendation as a terminal act, while general-purpose LLMs hallucinate product claims and default to generic promotional templates that fail to engage or persuade. We present VerbalValue, a sales-conversion-oriented virtual host that turns exceptional verbal ability into real commercial value, built on three contributions. First, we construct a domain knowledge base of product specifications and a curated sales terminology lexicon that anchor product-related responses in verified expertise. Second, we collect and annotate 1,475 live-commerce interactions spanning diverse viewer intents. Third, we fine-tune a large language model on this data to deliver empathetic, commercially oriented responses, adapting to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection. Experiments against GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Pro, and other baselines demonstrate gains of 23% on informativeness and 18% on factual correctness, with consistent advantages in tactfulness and viewer engagement.
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。