# PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning

arXiv: https://arxiv.org/abs/2006.16779 · HTML: https://mlsanity.com/paper/2006.16779/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 30 of 79)

- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark](https://mlsanity.com/paper/2110.08466/) (2021)
- [Rewarding Chatbots for Real-World Engagement with Millions of Users](https://mlsanity.com/paper/2303.06135/) (2023)
- [Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances](https://mlsanity.com/paper/2106.02227/) (2021)
- [InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning](https://mlsanity.com/paper/2205.12673/) (2022)
- [PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation](https://mlsanity.com/paper/2109.09519/) (2021)
- [Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks](https://mlsanity.com/paper/2202.08011/) (2022)
- [Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/2106.00291/) (2021)
- [EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training](https://mlsanity.com/paper/2108.01547/) (2021)
- [CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models](https://mlsanity.com/paper/2311.16832/) (2023)
- [Opportunities and Challenges in Neural Dialog Tutoring](https://mlsanity.com/paper/2301.09919/) (2023)
- [EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training](https://mlsanity.com/paper/2203.09313/) (2022)
- [Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models](https://mlsanity.com/paper/2305.17878/) (2023)
- ["How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations](https://mlsanity.com/paper/2109.13489/) (2021)
- [Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM](https://mlsanity.com/paper/2401.02994/) (2024)
- [A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models](https://mlsanity.com/paper/2311.16789/) (2023)
- [Amendable Generation for Dialogue State Tracking](https://mlsanity.com/paper/2110.15659/) (2021)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Learning to Select External Knowledge with Multi-Scale Negative Sampling](https://mlsanity.com/paper/2102.02096/) (2021)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency](https://mlsanity.com/paper/2106.02228/) (2021)
- [UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues](https://mlsanity.com/paper/2110.08032/) (2021)
- [TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations](https://mlsanity.com/paper/2112.12441/) (2021)
- [ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems](https://mlsanity.com/paper/2305.07797/) (2023)

## Abstract (arXiv)

To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained generation model is trained to learn response generation under the simplified framework of one-to-one mapping. In the second stage, a fine-grained generative model augmented with latent variables and an evaluation model are further trained to generate diverse responses and to select the best response, respectively. PLATO-2 was trained on both Chinese and English data, whose effectiveness and superiority are verified through comprehensive evaluations, achieving new state-of-the-art results.