# Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/1704.07130 · HTML: https://mlsanity.com/paper/1704.07130/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2017.

## Built on by (most cited first, 30 of 59)

- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.00783/) (2021)
- [CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems](https://mlsanity.com/paper/2103.15721/) (2021)
- [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024)
- [Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech](https://mlsanity.com/paper/2106.11783/) (2021)
- [Learning Rewards from Linguistic Feedback](https://mlsanity.com/paper/2009.14715/) (2020)
- [Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts](https://mlsanity.com/paper/2103.08115/) (2021)
- [ValueNet: A New Dataset for Human Value Driven Dialogue System](https://mlsanity.com/paper/2112.06346/) (2021)
- [Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2104.13095/) (2021)
- [Decision-Oriented Dialogue for Human-AI Collaboration](https://mlsanity.com/paper/2305.20076/) (2023)
- [DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network](https://mlsanity.com/paper/2108.09628/) (2021)
- [Improving Hyper-Relational Knowledge Graph Completion](https://mlsanity.com/paper/2104.08167/) (2021)
- [Geometry Interaction Knowledge Graph Embeddings](https://mlsanity.com/paper/2206.12418/) (2022)
- [Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy](https://mlsanity.com/paper/2204.07433/) (2022)
- [Reference-Centric Models for Grounded Collaborative Dialogue](https://mlsanity.com/paper/2109.05042/) (2021)
- [HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2210.09708/) (2022)
- [Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis](https://mlsanity.com/paper/2104.04676/) (2021)
- [Maintaining Common Ground in Dynamic Environments](https://mlsanity.com/paper/2105.14207/) (2021)
- [Analysis of Language Change in Collaborative Instruction Following](https://mlsanity.com/paper/2109.04452/) (2021)
- [Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World](https://mlsanity.com/paper/2404.00246/) (2024)
- [Measuring How (Not Just Whether) VLMs Build Common Ground](https://mlsanity.com/paper/2509.03805/) (2025)
- [MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games](https://mlsanity.com/paper/2602.24188/) (2026)
- [Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective](https://mlsanity.com/paper/2205.04105/) (2022)
- [Asking More Informative Questions for Grounded Retrieval](https://mlsanity.com/paper/2311.08584/) (2023)
- [Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication](https://mlsanity.com/paper/2405.14173/) (2024)
- [SPE: Symmetrical Prompt Enhancement for Fact Probing](https://mlsanity.com/paper/2211.07078/) (2022)
- [Symbolic Planning and Code Generation for Grounded Dialogue](https://mlsanity.com/paper/2310.17140/) (2023)
- [Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning](https://mlsanity.com/paper/2407.12703/) (2024)
- [Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization](https://mlsanity.com/paper/2412.15453/) (2024)

## Abstract (arXiv)

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.