# Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems

arXiv: https://arxiv.org/abs/2203.10610 · HTML: https://mlsanity.com/paper/2203.10610/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (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)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://mlsanity.com/paper/1506.06714/) (2015)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches](https://mlsanity.com/paper/1904.01172/) (2019)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [MATE: Multi-view Attention for Table Transformer Efficiency](https://mlsanity.com/paper/2109.04312/) (2021)
- [Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2002.10348/) (2020)
- [Global-to-local Memory Pointer Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1901.04713/) (2019)
- [Pointing the Unknown Words](https://mlsanity.com/paper/1603.08148/) (2016)
- [Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge](https://mlsanity.com/paper/2007.00849/) (2020)
- [DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs](https://mlsanity.com/paper/1910.00610/) (2019)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2010.01447/) (2020)

## Built on by (most cited first, 10 of 10)

- [Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2305.18846/) (2023)
- [RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning](https://mlsanity.com/paper/2310.13864/) (2023)
- [MidMed: Towards Mixed-Type Dialogues for Medical Consultation](https://mlsanity.com/paper/2306.02923/) (2023)
- [Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation](https://mlsanity.com/paper/2410.09350/) (2024)
- [On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL](https://mlsanity.com/paper/2404.02389/) (2024)
- [EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems](https://mlsanity.com/paper/2503.23078/) (2025)
- [A Data Source for Reasoning Embodied Agents](https://mlsanity.com/paper/2309.07974/) (2023)
- [Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2310.07659/) (2023)
- [Training Zero-Shot Generalizable End-to-End Task-Oriented Dialog System Without Turn-level Dialog Annotations](https://mlsanity.com/paper/2407.15055/) (2024)
- [Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach](https://mlsanity.com/paper/2511.23335/) (2025)

## Abstract (arXiv)

Users interacting with voice assistants today need to phrase their requests in a very specific manner to elicit an appropriate response. This limits the user experience, and is partly due to the lack of reasoning capabilities of dialogue platforms and the hand-crafted rules that require extensive labor. One possible way to improve user experience and relieve the manual efforts of designers is to build an end-to-end dialogue system that can do reasoning itself while perceiving user's utterances. In this work, we propose a novel method to incorporate the knowledge reasoning capability into dialogue systems in a more scalable and generalizable manner. Our proposed method allows a single transformer model to directly walk on a large-scale knowledge graph to generate responses. To the best of our knowledge, this is the first work to have transformer models generate responses by reasoning over differentiable knowledge graphs. We investigate the reasoning abilities of the proposed method on both task-oriented and domain-specific chit-chat dialogues. Empirical results show that this method can effectively and efficiently incorporate a knowledge graph into a dialogue system with fully-interpretable reasoning paths.