mlsanityData to 7 Oct 2026

Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

arXiv 1809.05296 ↗First posted 14 Sep 2018cs.CLcited by 49

Not on the map. Why?

Abstract (arXiv)

For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 6; 2024: 16; 2025: 2; 2026: 2.

49 papers.

Sort:

By area:

  1. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  2. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  3. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  4. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  5. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  6. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  7. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  8. 2024Disentangling Memory and Reasoning Ability in Large Language Modelscited by 43
  9. 2024VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generationcited by 40
  10. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  11. 2023Copy Is All You Needcited by 25
  12. 2023Personalized Large Language Model Assistant with Evolving Conditional Memorycited by 24
37 more
  1. 2021RetGen: A Joint framework for Retrieval and Grounded Text Generation Modelingcited by 22
  2. 2024Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generationcited by 19
  3. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  4. 2022PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentationcited by 14
  5. 2024Accelerating Retrieval-Augmented Generationcited by 14
  6. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  7. 2021IGA : An Intent-Guided Authoring Assistantcited by 12
  8. 2022Seamlessly Integrating Factual Information and Social Content with Persuasive Dialoguecited by 11
  9. 2021Transferable Persona-Grounded Dialogues via Grounded Minimal Editscited by 10
  10. 2023Diversify Question Generation with Retrieval-Augmented Style Transfercited by 10
  11. 2024Retrieval is Accurate Generationcited by 10
  12. 2021Sketch and Customize: A Counterfactual Story Generatorcited by 9
  13. 2021Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communicationcited by 9
  14. 2024XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tagscited by 9
  15. 2022AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialogcited by 8
  16. 2025Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Modelscited by 8
  17. 2021Towards Standard Criteria for human evaluation of Chatbots: A Surveycited by 6
  18. 2021Smoothing Dialogue States for Open Conversational Machine Readingcited by 6
  19. 2024VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoningcited by 6
  20. 2025UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generationcited by 6
  21. 2021EmpBot: A T5-based Empathetic Chatbot focusing on Sentimentscited by 5
  22. 2022ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extractioncited by 5
  23. 2024Towards a Robust Retrieval-Based Summarization Systemcited by 5
  24. 2024Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversationcited by 5
  25. 2024Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answeringcited by 5
  26. 2021Understanding and Improving the Exemplar-based Generation for Open-domain Conversationcited by 3
  27. 2022Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generationcited by 2
  28. 2024Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuningcited by 2
  29. 2024Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variabilitycited by 2
  30. 2021Partner Personas Generation for Diverse Dialogue Generationcited by 1
  31. 2022DISK: Domain-constrained Instance Sketch for Math Word Problem Generationcited by 1
  32. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
  33. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 0
  34. 2024A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generationcited by 0
  35. 2024PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generationcited by 0
  36. 2026PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversationcited by 0
  37. 2026Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspectivecited by 0