# Variational Learning for Unsupervised Knowledge Grounded Dialogs

arXiv: https://arxiv.org/abs/2112.00653 · HTML: https://mlsanity.com/paper/2112.00653/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 23 Nov 2021.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Variational Lossy Autoencoder](https://mlsanity.com/paper/1611.02731/) (2016)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [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)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [DoQA -- Accessing Domain-Specific FAQs via Conversational QA](https://mlsanity.com/paper/2005.01328/) (2020)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [Zero-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2008.12918/) (2020)
- [Multi-level Memory for Task Oriented Dialogs](https://mlsanity.com/paper/1810.10647/) (2018)
- [Unsupervised Learning of KB Queries in Task-Oriented Dialogs](https://mlsanity.com/paper/2005.00123/) (2020)

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

- [Efficient and Accurate Memorable Conversation Model using DPO based on sLLM](https://mlsanity.com/paper/2407.06537/) (2024)
- [Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation](https://mlsanity.com/paper/2508.18168/) (2025)
- [Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://mlsanity.com/paper/2204.02710/) (2022)

## Abstract (arXiv)

Recent methods for knowledge grounded dialogs generate responses by incorporating information from an external textual document. These methods do not require the exact document to be known during training and rely on the use of a retrieval system to fetch relevant documents from a large index. The documents used to generate the responses are modeled as latent variables whose prior probabilities need to be estimated. Models such as RAG and REALM, marginalize the document probabilities over the documents retrieved from the index to define the log likelihood loss function which is optimized end-to-end. In this paper, we develop a variational approach to the above technique wherein, we instead maximize the Evidence Lower bound (ELBO). Using a collection of three publicly available open-conversation datasets, we demonstrate how the posterior distribution, that has information from the ground-truth response, allows for a better approximation of the objective function during training. To overcome the challenges associated with sampling over a large knowledge collection, we develop an efficient approach to approximate the ELBO. To the best of our knowledge we are the first to apply variational training for open-scale unsupervised knowledge grounded dialog systems.