# Ottilie: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce

arXiv: https://arxiv.org/abs/2605.14542 · HTML: https://mlsanity.com/paper/2605.14542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 8 of 8)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion](https://mlsanity.com/paper/2007.04032/) (2020)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [HOTVCOM: Generating Buzzworthy Comments for Videos](https://mlsanity.com/paper/2409.15196/) (2024)
- [Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges](https://mlsanity.com/paper/2508.00454/) (2025)
- [Retrieval Augmented Conversational Recommendation with Reinforcement Learning](https://mlsanity.com/paper/2604.04457/) (2026)
- [Contextually Aware E-Commerce Product Question Answering using RAG](https://mlsanity.com/paper/2508.01990/) (2025)

## Abstract (arXiv)

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 Ottilie, a sales-conversion-oriented virtual host for Chinese beauty live commerce that grounds product responses in a verified knowledge base, adapts discourse strategy to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection, and supervises all four output fields simultaneously within a structured generation framework. Experiments demonstrate gains of 14% on informativeness and 5% on factual correctness, with consistent advantages in tactfulness and viewer engagement. Ottilie has been deployed as an autonomous English-language host on Twitch, where the same fine-tuned model runs unattended on a single commodity GPU and promotes the company's own product; we report how the system adapted to a new language, market, and product without retraining, and what the deployment revealed about latency and adversarial chat.