Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Chen, Yuyan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.14542
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916012132139008
author Chen, Yuyan
author_facet Chen, Yuyan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14542
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VerbalValue: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce
Chen, Yuyan
Artificial Intelligence
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.
title VerbalValue: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce
topic Artificial Intelligence
url https://arxiv.org/abs/2605.14542