mlsanityData to 7 Oct 2026

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training

arXiv 2108.01547 ↗First posted 3 Aug 2021cs.CL cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones. In this paper, we propose EVA, a Chinese dialogue system that contains the largest Chinese pre-trained dialogue model with 2.8B parameters. To build this model, we collect the largest Chinese dialogue dataset named WDC-Dialogue from various public social media. This dataset contains 1.4B context-response pairs and is used as the pre-training corpus of EVA. Extensive experiments on automatic and human evaluation show that EVA outperforms other Chinese pre-trained dialogue models especially in the multi-turn interaction of human-bot conversations.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 20 of its 26 references that are in the map. First posted on arXiv 3 Aug 2021.

Builds on

20 of 26 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  6. 2017Mixed Precision Trainingcited by 1,135
  7. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  8. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  9. 2020Recipes for building an open-domain chatbotcited by 593
  10. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  11. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  12. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
8 more
  1. 2015A Neural Conversational Modelcited by 195
  2. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  3. 2016Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbotscited by 103
  4. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  5. 2020A Large-Scale Chinese Short-Text Conversation Datasetcited by 77
  6. 2019Personalized Dialogue Generation with Diversified Traitscited by 73
  7. 2020CPM: A Large-scale Generative Chinese Pre-trained Language Modelcited by 60
  8. 2020Pchatbot: A Large-Scale Dataset for Personalized Chatbotcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 17; 2023: 13; 2024: 2; 2025: 0; 2026: 1.

34 papers.

Sort:

By area:

  1. 2023Safety Assessment of Chinese Large Language Modelscited by 82
  2. 2022AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversationcited by 79
  3. 2022COLD: A Benchmark for Chinese Offensive Language Detectioncited by 74
  4. 2023PanGu-Sigma: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computingcited by 55
  5. 2023BiasAsker: Measuring the Bias in Conversational AI Systemcited by 52
  6. 2021PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generationcited by 37
  7. 2022Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarkscited by 36
  8. 2023CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Modelscited by 34
  9. 2022EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Trainingcited by 31
  10. 2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
  11. 2022Rethinking and Refining the Distinct Metriccited by 27
  12. 2022CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AIcited by 25
22 more
  1. 2023CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Modelscited by 25
  2. 2023ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Humancited by 14
  3. 2022Towards Boosting the Open-Domain Chatbot with Human Feedbackcited by 11
  4. 2022Estimating Soft Labels for Out-of-Domain Intent Detectioncited by 11
  5. 2022CDConv: A Benchmark for Contradiction Detection in Chinese Conversationscited by 10
  6. 2023A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairmentcited by 10
  7. 2022PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Modelcited by 9
  8. 2024Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generationcited by 9
  9. 2022Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialoguecited by 8
  10. 2022Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generationcited by 8
  11. 2023TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real Worldcited by 7
  12. 2023UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learningcited by 6
  13. 2022A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigmscited by 4
  14. 2023Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generationcited by 4
  15. 2024A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generationcited by 3
  16. 2022PLATO-K: Internal and External Knowledge Enhanced Dialogue Generationcited by 2
  17. 2022Semi-Supervised Lifelong Language Learningcited by 1
  18. 2026A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairmentcited by 1
  19. 2022Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)cited by 0
  20. 2023Topic-switch adapted Japanese Dialogue System based on PLATO-2cited by 0
  21. 2023InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admissioncited by 0
  22. 2023Re3Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-trainingcited by 0