# Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation arXiv: https://arxiv.org/abs/2306.16195 ยท HTML: https://mlsanity.com/paper/2306.16195/ ## Key facts - Cited by 16 papers in the map (data through 14 Oct 2026). - Builds on 22 of its 36 references that are in the map. - First posted on arXiv 28 Jun 2023. ## Builds on (most cited first, 22 of 22) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [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) - [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019) - [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014) - [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021) - [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019) - [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017) - [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021) - [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018) - [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020) - [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://mlsanity.com/paper/1911.02707/) (2019) - [DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs](https://mlsanity.com/paper/1910.00610/) (2019) - [Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts](https://mlsanity.com/paper/2203.07285/) (2022) - [Flexible End-to-End Dialogue System for Knowledge Grounded Conversation](https://mlsanity.com/paper/1709.04264/) (2017) - [EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention](https://mlsanity.com/paper/2210.12463/) (2022) - [TwistList: Resources and Baselines for Tongue Twister Generation](https://mlsanity.com/paper/2306.03457/) (2023) - [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022) - [NGEP: A Graph-based Event Planning Framework for Story Generation](https://mlsanity.com/paper/2210.10602/) (2022) - [Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics](https://mlsanity.com/paper/2210.10618/) (2022) - [Terminology-aware Medical Dialogue Generation](https://mlsanity.com/paper/2210.15551/) (2022) - [CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation](https://mlsanity.com/paper/2305.06294/) (2023) ## Built on by (most cited first, 16 of 16) - [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025) - [Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices](https://mlsanity.com/paper/2408.09169/) (2024) - [SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation](https://mlsanity.com/paper/2405.15924/) (2024) - [Improving Medical Dialogue Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2309.10608/) (2023) - [Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Papers](https://mlsanity.com/paper/2310.15684/) (2023) - [Enhancing Biomedical Lay Summarisation with External Knowledge Graphs](https://mlsanity.com/paper/2310.15702/) (2023) - [A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation](https://mlsanity.com/paper/2311.11271/) (2023) - [WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation](https://mlsanity.com/paper/2503.19065/) (2025) - [Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth](https://mlsanity.com/paper/2509.03867/) (2025) - [Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases](https://mlsanity.com/paper/2403.13901/) (2024) - [DRE: An Effective Dual-Refined Method for Integrating Small and Large Language Models in Open-Domain Dialogue Evaluation](https://mlsanity.com/paper/2506.04516/) (2025) - [ACL Anthology Helper: A Tool to Retrieve and Manage Literature from ACL Anthology](https://mlsanity.com/paper/2310.20467/) (2023) - [UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems](https://mlsanity.com/paper/2401.06811/) (2024) - [BioMNER: A Dataset for Biomedical Method Entity Recognition](https://mlsanity.com/paper/2406.20038/) (2024) - [Matching Game Preferences Through Dialogical Large Language Models: A Perspective](https://mlsanity.com/paper/2507.20000/) (2025) - [HyPE: Category-Aware Hypergraph Encoding with Persistent Edge Embeddings for Persona-Grounded Dialogue](https://mlsanity.com/paper/2606.13142/) (2026) ## Abstract (arXiv) Incorporating external graph knowledge into neural chatbot models has been proven effective for enhancing dialogue generation. However, in conventional graph neural networks (GNNs), message passing on a graph is independent from text, resulting in the graph representation hidden space differing from that of the text. This training regime of existing models therefore leads to a semantic gap between graph knowledge and text. In this study, we propose a novel framework for knowledge graph enhanced dialogue generation. We dynamically construct a multi-hop knowledge graph with pseudo nodes to involve the language model in feature aggregation within the graph at all steps. To avoid the semantic biases caused by learning on vanilla subgraphs, the proposed framework applies hierarchical graph attention to aggregate graph features on pseudo nodes and then attains a global feature. Therefore, the framework can better utilise the heterogeneous features from both the post and external graph knowledge. Extensive experiments demonstrate that our framework outperforms state-of-the-art (SOTA) baselines on dialogue generation. Further analysis also shows that our representation learning framework can fill the semantic gap by coagulating representations of both text and graph knowledge. Moreover, the language model also learns how to better select knowledge triples for a more informative response via exploiting subgraph patterns within our feature aggregation process. Our code and resources are available at https://github.com/tangg555/SaBART.