# Robust Conversational AI with Grounded Text Generation

arXiv: https://arxiv.org/abs/2009.03457 · HTML: https://mlsanity.com/paper/2009.03457/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [Neural Approaches to Conversational Information Retrieval](https://mlsanity.com/paper/2201.05176/) (2022)
- [RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling](https://mlsanity.com/paper/2105.06597/) (2021)
- [Correctness is not Faithfulness in RAG Attributions](https://mlsanity.com/paper/2412.18004/) (2024)
- [Event Transition Planning for Open-ended Text Generation](https://mlsanity.com/paper/2204.09453/) (2022)
- [SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching](https://mlsanity.com/paper/2110.11514/) (2021)
- [Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans](https://mlsanity.com/paper/2306.01729/) (2023)
- [Position Paper: Agent AI Towards a Holistic Intelligence](https://mlsanity.com/paper/2403.00833/) (2024)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)

## Abstract (arXiv)

This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transformer neural network as its backbone, combined with symbol-manipulation modules for knowledge base inference and prior knowledge encoding, to generate responses grounded in dialog belief state and real-world knowledge for task completion. GTG is pre-trained on large amounts of raw text and human conversational data, and can be fine-tuned to complete a wide range of tasks. The hybrid approach and its variants are being developed simultaneously by multiple research teams. The primary results reported on task-oriented dialog benchmarks are very promising, demonstrating the big potential of this approach. This article provides an overview of this progress and discusses related methods and technologies that can be incorporated for building robust conversational AI systems.