# The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

arXiv: https://arxiv.org/abs/1812.08989 · HTML: https://mlsanity.com/paper/1812.08989/

## Key facts

- Cited by 172 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2018.

## Built on by (most cited first, 30 of 172)

- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [Human-centric Dialog Training via Offline Reinforcement Learning](https://mlsanity.com/paper/2010.05848/) (2020)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations](https://mlsanity.com/paper/2106.01978/) (2021)
- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [Dialogue Response Ranking Training with Large-Scale Human Feedback Data](https://mlsanity.com/paper/2009.06978/) (2020)
- [Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation](https://mlsanity.com/paper/2204.12749/) (2022)
- [Is ChatGPT Equipped with Emotional Dialogue Capabilities?](https://mlsanity.com/paper/2304.09582/) (2023)
- [Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data](https://mlsanity.com/paper/2301.05843/) (2023)
- [Faithful Persona-based Conversational Dataset Generation with Large Language Models](https://mlsanity.com/paper/2312.10007/) (2023)
- [Biomedical Question Answering: A Survey of Approaches and Challenges](https://mlsanity.com/paper/2102.05281/) (2021)
- [CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation](https://mlsanity.com/paper/2105.08316/) (2021)
- [A Full-duplex Speech Dialogue Scheme Based On Large Language Models](https://mlsanity.com/paper/2405.19487/) (2024)
- [One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles](https://mlsanity.com/paper/2108.09355/) (2021)
- [PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation](https://mlsanity.com/paper/2109.09519/) (2021)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations](https://mlsanity.com/paper/2310.20494/) (2023)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [ValueNet: A New Dataset for Human Value Driven Dialogue System](https://mlsanity.com/paper/2112.06346/) (2021)
- [Revealing Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2104.08728/) (2021)
- [Artificial Influence: An Analysis Of AI-Driven Persuasion](https://mlsanity.com/paper/2303.08721/) (2023)
- [Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation](https://mlsanity.com/paper/2112.07924/) (2021)
- [Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI](https://mlsanity.com/paper/2309.12444/) (2023)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)

## Abstract (arXiv)

This paper describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient (IQ) and emotional quotient (EQ) in system design, cast human-machine social chat as decision-making over Markov Decision Processes (MDPs), and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key components including dialogue manager, core chat, skills, and an empathetic computing module. We show how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations. Since her launch in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them. Analysis of large scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.