# There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning

arXiv: https://arxiv.org/abs/2210.12459 · HTML: https://mlsanity.com/paper/2210.12459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 22 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning](https://mlsanity.com/paper/2006.16779/) (2020)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2002.10348/) (2020)
- [A Controllable Model of Grounded Response Generation](https://mlsanity.com/paper/2005.00613/) (2020)
- [Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References](https://mlsanity.com/paper/1907.10568/) (2019)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading](https://mlsanity.com/paper/1906.02738/) (2019)
- [Reason first, then respond: Modular Generation for Knowledge-infused Dialogue](https://mlsanity.com/paper/2111.05204/) (2021)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [On Unifying Deep Generative Models](https://mlsanity.com/paper/1706.00550/) (2017)
- [Select and Attend: Towards Controllable Content Selection in Text Generation](https://mlsanity.com/paper/1909.04453/) (2019)
- [Multi-Referenced Training for Dialogue Response Generation](https://mlsanity.com/paper/2009.07117/) (2020)

## Built on by (most cited first, 2 of 2)

- [Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation](https://mlsanity.com/paper/2310.08943/) (2023)
- [Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach](https://mlsanity.com/paper/2511.23335/) (2025)

## Abstract (arXiv)

Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, the existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multi-reference KGC dataset and propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the one-to-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.