mlsanityData to 14 Oct 2026

Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation

arXiv 2301.04907 ↗First posted 12 Jan 2023cs.CL cs.HCcited by 14

Not on the map. Why?

Abstract (arXiv)

Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and semantics, and requires rare emotion-annotated large-scale dialogue corpus. Inspired by the "think twice" behavior in human dialogue, we propose a two-stage conversational agent for the generation of emotional dialogue. Firstly, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics. Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis. Experimental results on the DailyDialog and EmpatheticDialogues datasets demonstrate that the proposed conversational outperforms the comparison models in emotion generation and maintains the semantic performance in automatic and human evaluations.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 12 Jan 2023.

Builds on

39 of 59 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  5. 2018Hierarchical Neural Story Generationcited by 1,193
  6. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  7. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  8. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  10. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  11. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  12. 2021Towards Emotional Support Dialog Systemscited by 299
27 more
  1. 2017Toward Controlled Generation of Textcited by 272
  2. 2018DialogueRNN: An Attentive RNN for Emotion Detection in Conversationscited by 218
  3. 2019DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversationcited by 186
  4. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  5. 2020COSMIC: COmmonSense knowledge for eMotion Identification in Conversationscited by 136
  6. 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 116
  7. 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
  8. 2019MoEL: Mixture of Empathetic Listenerscited by 91
  9. 2021CEM: Commonsense-aware Empathetic Response Generationcited by 89
  10. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 85
  11. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  12. 2021DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversationscited by 71
  13. 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
  14. 2022Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversationcited by 56
  15. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  16. 2020Exploring Controllable Text Generation Techniquescited by 55
  17. 2020SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysiscited by 54
  18. 2020How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Contextcited by 53
  19. 2017Affect-LM: A Neural Language Model for Customizable Affective Text Generationcited by 50
  20. 2020Knowledge Bridging for Empathetic Dialogue Generationcited by 50
  21. 2019"Mask and Infill" : Applying Masked Language Model to Sentiment Transfercited by 48
  22. 2016GLEU Without Tuningcited by 24
  23. 2018An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Losscited by 21
  24. 2022FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversationcited by 18
  25. 2017Affective Neural Response Generationcited by 17
  26. 2018Learning Sentiment Memories for Sentiment Modification without Parallel Datacited by 10
  27. 2019Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvementscited by 42
  2. 2023Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Personacited by 24
  3. 2023Leveraging Large Language Models for Automated Dialogue Analysiscited by 14
  4. 2024Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuningcited by 11
  5. 2024Synth-Empathy: Towards High-Quality Synthetic Empathy Datacited by 10
  6. 2023Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theorycited by 7
  7. 2025From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Modelscited by 6
  8. 2024Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Modelscited by 5
  9. 2026ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinementcited by 5
  10. 2025Modeling the One-to-Many Property in Open-Domain Dialogue with LLMscited by 3
  11. 2025Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modelingcited by 1
  12. 2024Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Datacited by 0
2 more
  1. 2024CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Modelscited by 0
  2. 2025Semantic Differentiation in Speech Emotion Recognition: Insights from Descriptive and Expressive Speech Rolescited by 0