mlsanityData to 7 Oct 2026

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation

arXiv 2306.10317 ↗First posted 17 Jun 2023cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Existing controllable dialogue generation work focuses on the single-attribute control and lacks generalization capability to out-of-distribution multiple attribute combinations. In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations. We propose a prompt-based disentangled controllable dialogue generation model, DCG. It learns attribute concept composition by generating attribute-oriented prompt vectors and uses a disentanglement loss to disentangle different attributes for better generalization. Besides, we design a unified reference-free evaluation framework for multiple attributes with different levels of granularities. Experiment results on two benchmarks prove the effectiveness of our method and the evaluation metric.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 17 Jun 2023.

Builds on

34 of 44 references.

References · 34

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  8. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  10. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  11. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  12. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
22 more
  1. 2020Recipes for building an open-domain chatbotcited by 593
  2. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  3. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  4. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  5. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  6. 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
  7. 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
  8. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  9. 2017ParlAI: A Dialog Research Software Platformcited by 139
  10. 2019Personalizing Dialogue Agents via Meta-Learningcited by 83
  11. 2020Span-based Semantic Parsing for Compositional Generalizationcited by 77
  12. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  13. 2020UNION: An Unreferenced Metric for Evaluating Open-ended Story Generationcited by 60
  14. 2020CoCon: A Self-Supervised Approach for Controlled Text Generationcited by 47
  15. 2020Improving Compositional Generalization in Semantic Parsingcited by 42
  16. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  17. 2021Disentangled Sequence to Sequence Learning for Compositional Generalizationcited by 30
  18. 2022CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generationcited by 29
  19. 2021Control Prefixes for Parameter-Efficient Text Generationcited by 23
  20. 2022Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generationcited by 22
  21. 2021Improving Compositional Generalization with Self-Training for Data-to-Text Generationcited by 19
  22. 2021SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 2; 2026: 2.

7 papers.

  1. 2024Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practicescited by 19
  2. 2023Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approachcited by 7
  3. 2025Position: LLMs Can be Good Tutors in English Educationcited by 6
  4. 2024MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learningcited by 4
  5. 2025ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generationcited by 3
  6. 2026Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMscited by 1
  7. 2026The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generationcited by 0