# Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

arXiv: https://arxiv.org/abs/2009.13656 · HTML: https://mlsanity.com/paper/2009.13656/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 30 of 35)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [Contrastive Learning Reduces Hallucination in Conversations](https://mlsanity.com/paper/2212.10400/) (2022)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters](https://mlsanity.com/paper/2105.06232/) (2021)
- [DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation](https://mlsanity.com/paper/2204.09149/) (2022)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Q-TOD: A Query-driven Task-oriented Dialogue System](https://mlsanity.com/paper/2210.07564/) (2022)
- [Medical Dialogue Response Generation with Pivotal Information Recalling](https://mlsanity.com/paper/2206.08611/) (2022)
- [Autoregressive Entity Generation for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2209.08708/) (2022)
- [Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues](https://mlsanity.com/paper/2305.13690/) (2023)
- [Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2212.08120/) (2022)
- [Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2305.10149/) (2023)
- [CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System](https://mlsanity.com/paper/2106.03530/) (2021)
- [Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation](https://mlsanity.com/paper/2108.10808/) (2021)
- [A Comparative Study on Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2201.08687/) (2022)
- [Knowledge-grounded Dialog State Tracking](https://mlsanity.com/paper/2210.06656/) (2022)
- [GraphWOZ: Dialogue Management with Conversational Knowledge Graphs](https://mlsanity.com/paper/2211.12852/) (2022)
- [InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.08885/) (2023)
- [Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling](https://mlsanity.com/paper/2412.02415/) (2024)
- [Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems](https://mlsanity.com/paper/2405.15585/) (2024)
- [Language Surgery in Multilingual Large Language Models](https://mlsanity.com/paper/2506.12450/) (2025)
- [High-Quality Diversification for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2106.00891/) (2021)
- [Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?](https://mlsanity.com/paper/2210.12942/) (2022)
- [Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2310.08877/) (2023)
- [Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.14528/) (2023)
- [IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2311.00958/) (2023)
- [Advising Agent for Service-Providing Live-Chat Operators](https://mlsanity.com/paper/2105.03986/) (2021)

## Abstract (arXiv)

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. End-to-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via fine-tuning. We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets.