# Understanding and Improving the Exemplar-based Generation for Open-domain Conversation

arXiv: https://arxiv.org/abs/2112.06723 · HTML: https://mlsanity.com/paper/2112.06723/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring](https://mlsanity.com/paper/1905.01969/) (2019)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills](https://mlsanity.com/paper/2004.08449/) (2020)
- [Training Millions of Personalized Dialogue Agents](https://mlsanity.com/paper/1809.01984/) (2018)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Generating Sentences by Editing Prototypes](https://mlsanity.com/paper/1709.08878/) (2017)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://mlsanity.com/paper/1808.04776/) (2018)
- [End-to-End Training of Neural Retrievers for Open-Domain Question Answering](https://mlsanity.com/paper/2101.00408/) (2021)
- [Augmenting Transformers with KNN-Based Composite Memory for Dialogue](https://mlsanity.com/paper/2004.12744/) (2020)
- [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://mlsanity.com/paper/1809.05296/) (2018)
- [Importance of Search and Evaluation Strategies in Neural Dialogue Modeling](https://mlsanity.com/paper/1811.00907/) (2018)
- [Response Generation by Context-aware Prototype Editing](https://mlsanity.com/paper/1806.07042/) (2018)
- [Controlling Dialogue Generation with Semantic Exemplars](https://mlsanity.com/paper/2008.09075/) (2020)
- [Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation](https://mlsanity.com/paper/2005.10716/) (2020)
- [Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation](https://mlsanity.com/paper/1606.00776/) (2016)
- [Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation](https://mlsanity.com/paper/2108.12582/) (2021)

## Built on by (most cited first, 3 of 3)

- [Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models](https://mlsanity.com/paper/2205.00176/) (2022)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos](https://mlsanity.com/paper/2303.09713/) (2023)

## Abstract (arXiv)

Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the retrieved exemplars while generating responses or produce responses over-fitted to the retrieved exemplars. In this paper, we argue that these drawbacks are derived from the one-to-many problem of the open-domain conversation. When the retrieved exemplar is relevant to the given context yet significantly different from the gold response, the exemplar-based generative models are trained to ignore the exemplar since the exemplar is not helpful for generating the gold response. On the other hand, when the retrieved exemplar is lexically similar to the gold response, the generative models are trained to rely on the exemplar highly. Therefore, we propose a training method selecting exemplars that are semantically relevant to the gold response but lexically distanced from the gold response to mitigate the above disadvantages. In the training phase, our proposed training method first uses the gold response instead of dialogue context as a query to select exemplars that are semantically relevant to the gold response. And then, it eliminates the exemplars that lexically resemble the gold responses to alleviate the dependency of the generative models on that exemplars. The remaining exemplars could be irrelevant to the given context since they are searched depending on the gold response. Thus, our proposed training method further utilizes the relevance scores between the given context and the exemplars to penalize the irrelevant exemplars. Extensive experiments demonstrate that our proposed training method alleviates the drawbacks of the existing exemplar-based generative models and significantly improves the performance in terms of appropriateness and informativeness.