# A Comparative Study on Language Models for Task-Oriented Dialogue Systems

arXiv: https://arxiv.org/abs/2201.08687 · HTML: https://mlsanity.com/paper/2201.08687/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 21 Jan 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [OpenNMT: Open-source Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1709.03815/) (2017)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems](https://mlsanity.com/paper/1911.09273/) (2019)
- [Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.13656/) (2020)
- [Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever](https://mlsanity.com/paper/1909.06762/) (2019)
- [Disentangling Language and Knowledge in Task-Oriented Dialogs](https://mlsanity.com/paper/1805.01216/) (2018)
- [Multi-level Memory for Task Oriented Dialogs](https://mlsanity.com/paper/1810.10647/) (2018)
- [Sequence-to-Sequence Learning for Indonesian Automatic Question Generator](https://mlsanity.com/paper/2009.13889/) (2020)

## Built on by (most cited first, 5 of 5)

- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System](https://mlsanity.com/paper/2306.09821/) (2023)
- [Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering](https://mlsanity.com/paper/2308.15231/) (2023)
- [Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture](https://mlsanity.com/paper/2409.18568/) (2024)
- [RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models](https://mlsanity.com/paper/2505.08463/) (2025)

## Abstract (arXiv)

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can be used for end-to-end training without relying on dialogue state tracking to track the dialogue history but allowing the language models to generate responses according to the context given as input. This paper conducts a comparative study to show the effectiveness and strength of using recent pretrained models for fine-tuning, such as BART and T5, on endto-end ToD systems. The experimental results show substantial performance improvements after language model fine-tuning. The models produce more fluent responses after adding knowledge to the context that guides the model to avoid hallucination and generate accurate entities in the generated responses. Furthermore, we found that BART and T5 outperform GPT-based models in BLEU and F1 scores and achieve state-of-the-art performance in a ToD system.