mlsanityData to 14 Oct 2026

Controllable Mixed-Initiative Dialogue Generation through Prompting

arXiv 2305.04147 ↗First posted 6 May 2023cs.CL cs.AI cs.HCcited by 32

Not on the map. Why?

Abstract (arXiv)

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. However, these supervised generation models are limited by the cost and quality of data annotation. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation. We formalize prompt construction for controllable mixed-initiative dialogue. Our findings show improvements over fine-tuning and ground truth responses according to human evaluation and automatic metrics for two tasks: PersuasionForGood and Emotional Support Conversations.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 49 of its 55 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

49 of 55 references.

References · 49

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2022Emergent Abilities of Large Language Modelscited by 2,512
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  10. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  12. 2015Generating Sentences from a Continuous Spacecited by 612
37 more
  1. 2020Recipes for building an open-domain chatbotcited by 593
  2. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  3. 2021Towards Emotional Support Dialog Systemscited by 299
  4. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  5. 2021Internet-Augmented Dialogue Generationcited by 217
  6. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 209
  7. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 204
  8. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  9. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 168
  10. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 149
  11. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  12. 2020Towards Conversational Recommendation over Multi-Type Dialogscited by 107
  13. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  14. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  15. 2021A Comprehensive Assessment of Dialog Evaluation Metricscited by 90
  16. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  17. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  18. 2021A Plug-and-Play Method for Controlled Text Generationcited by 56
  19. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  20. 2019Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attentioncited by 44
  21. 2022Weakly Supervised Data Augmentation Through Prompting for Dialogue Understandingcited by 32
  22. 2021Annotation Inconsistency and Entity Bias in MultiWOZcited by 30
  23. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  24. 2020Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategiescited by 29
  25. 2021Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generationcited by 29
  26. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelscited by 27
  27. 2022Multi-Stage Prompting for Knowledgeable Dialogue Generationcited by 22
  28. 2018Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learningcited by 21
  29. 2021Towards Quantifiable Dialogue Coherence Evaluationcited by 21
  30. 2022LAD: Language Models as Data for Zero-Shot Dialogcited by 18
  31. 2019Planning for Goal-Oriented Dialogue Systemscited by 15
  32. 2019Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answeringcited by 15
  33. 2022Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Modelscited by 13
  34. 2021LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcingcited by 11
  35. 2022Seamlessly Integrating Factual Information and Social Content with Persuasive Dialoguecited by 11
  36. 2022Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoningcited by 6
  37. 2022Improving Bot Response Contradiction Detection via Utterance Rewritingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 11; 2025: 9; 2026: 6.

32 papers.

Sort:

By area:

  1. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 124
  2. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  3. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  4. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  5. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  6. 2024Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Trainingcited by 57
  7. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  8. 2024Towards Human-centered Proactive Conversational Agentscited by 49
  9. 2025Creating General User Models from Computer Usecited by 44
  10. 2025Navigating Rifts in Human-LLM Grounding: Study and Benchmarkcited by 29
  11. 2024Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspectivecited by 25
  12. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
20 more
  1. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  2. 2023COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goalcited by 18
  3. 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
  4. 2024Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrievalcited by 14
  5. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  6. 2023Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Datacited by 9
  7. 2024EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamicscited by 9
  8. 2024X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agentscited by 6
  9. 2025KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapycited by 5
  10. 2025Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewardscited by 5
  11. 2026Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluationcited by 2
  12. 2025BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrumcited by 1
  13. 2025Mixed-Initiative Dialog for Human-Robot Collaborative Manipulationcited by 1
  14. 2024Mix-Initiative Response Generation with Dynamic Prefix Tuningcited by 0
  15. 2025Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimationscited by 0
  16. 2026Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytellingcited by 0
  17. 2026Alignment has a Fantasia Problemcited by 0
  18. 2026A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principlescited by 0
  19. 2026UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systemscited by 0
  20. 2026Proactive Dialogue Policy Optimization via Cognitive-State Transitioncited by 0