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

arXiv: https://arxiv.org/abs/1809.05296 · HTML: https://mlsanity.com/paper/1809.05296/

## Key facts

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

## Built on by (most cited first, 30 of 49)

- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [Disentangling Memory and Reasoning Ability in Large Language Models](https://mlsanity.com/paper/2411.13504/) (2024)
- [VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.10704/) (2024)
- [RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards](https://mlsanity.com/paper/2410.13509/) (2024)
- [Copy Is All You Need](https://mlsanity.com/paper/2307.06962/) (2023)
- [Personalized Large Language Model Assistant with Evolving Conditional Memory](https://mlsanity.com/paper/2312.17257/) (2023)
- [RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling](https://mlsanity.com/paper/2105.06597/) (2021)
- [Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation](https://mlsanity.com/paper/2402.18150/) (2024)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation](https://mlsanity.com/paper/2208.08110/) (2022)
- [Accelerating Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15246/) (2024)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [IGA : An Intent-Guided Authoring Assistant](https://mlsanity.com/paper/2104.07000/) (2021)
- [Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue](https://mlsanity.com/paper/2203.07657/) (2022)
- [Transferable Persona-Grounded Dialogues via Grounded Minimal Edits](https://mlsanity.com/paper/2109.07713/) (2021)
- [Diversify Question Generation with Retrieval-Augmented Style Transfer](https://mlsanity.com/paper/2310.14503/) (2023)
- [Retrieval is Accurate Generation](https://mlsanity.com/paper/2402.17532/) (2024)
- [Sketch and Customize: A Counterfactual Story Generator](https://mlsanity.com/paper/2104.00929/) (2021)
- [Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication](https://mlsanity.com/paper/2106.11791/) (2021)
- [XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags](https://mlsanity.com/paper/2406.03776/) (2024)
- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models](https://mlsanity.com/paper/2502.18817/) (2025)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Smoothing Dialogue States for Open Conversational Machine Reading](https://mlsanity.com/paper/2108.12599/) (2021)

## 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.