# Are LLMs All You Need for Task-Oriented Dialogue?

arXiv: https://arxiv.org/abs/2304.06556 · HTML: https://mlsanity.com/paper/2304.06556/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 54 references that are in the map.
- First posted on arXiv 13 Apr 2023.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Survey on Evaluation Methods for Dialogue Systems](https://mlsanity.com/paper/1905.04071/) (2019)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [A Sequence-to-Sequence Approach to Dialogue State Tracking](https://mlsanity.com/paper/2011.09553/) (2020)
- [Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2008.06239/) (2020)
- [Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning](https://mlsanity.com/paper/1702.03274/) (2017)
- [AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models](https://mlsanity.com/paper/2102.05126/) (2021)
- [Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog](https://mlsanity.com/paper/2205.10400/) (2022)

## Built on by (most cited first, 30 of 54)

- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [A Survey of Text Watermarking in the Era of Large Language Models](https://mlsanity.com/paper/2312.07913/) (2023)
- [Large Language Models Meet NLP: A Survey](https://mlsanity.com/paper/2405.12819/) (2024)
- [Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue](https://mlsanity.com/paper/2402.17262/) (2024)
- [BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering](https://mlsanity.com/paper/2402.11129/) (2024)
- [DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues](https://mlsanity.com/paper/2405.13028/) (2024)
- [Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation](https://mlsanity.com/paper/2405.13037/) (2024)
- [OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking](https://mlsanity.com/paper/2311.09758/) (2023)
- [Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications](https://mlsanity.com/paper/2406.10300/) (2024)
- [Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges](https://mlsanity.com/paper/2505.13328/) (2025)
- [Improving Tool Retrieval by Leveraging Large Language Models for Query Generation](https://mlsanity.com/paper/2412.03573/) (2024)
- [Agent Guide: A Simple Agent Behavioral Watermarking Framework](https://mlsanity.com/paper/2504.05871/) (2025)
- [TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons](https://mlsanity.com/paper/2504.19982/) (2025)
- [A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions](https://mlsanity.com/paper/2504.16939/) (2025)
- [AgentMark: Utility-Preserving Behavioral Watermarking for Agents](https://mlsanity.com/paper/2601.03294/) (2026)
- [Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue](https://mlsanity.com/paper/2406.06399/) (2024)
- [DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi](https://mlsanity.com/paper/2503.04768/) (2025)
- [Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models](https://mlsanity.com/paper/2404.14772/) (2024)
- [HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals](https://mlsanity.com/paper/2411.07152/) (2024)
- [Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel](https://mlsanity.com/paper/2404.15219/) (2024)
- [Developing a Tutoring Dialog Dataset to Optimize LLMs for Educational Use](https://mlsanity.com/paper/2410.19231/) (2024)
- [Chitchat as Interference: Adding User Backstories to Task-Oriented Dialogues](https://mlsanity.com/paper/2402.15248/) (2024)
- [Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems](https://mlsanity.com/paper/2405.15585/) (2024)
- [Confidence Estimation for LLM-Based Dialogue State Tracking](https://mlsanity.com/paper/2409.09629/) (2024)
- [Multi-Designated Detector Watermarking for Language Models](https://mlsanity.com/paper/2409.17518/) (2024)
- [clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations](https://mlsanity.com/paper/2505.05445/) (2025)
- [SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU](https://mlsanity.com/paper/2311.09502/) (2023)
- [Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue](https://mlsanity.com/paper/2406.14457/) (2024)
- [Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets](https://mlsanity.com/paper/2407.05674/) (2024)

## Abstract (arXiv)

Instructions-tuned Large Language Models (LLMs) gained recently huge popularity thanks to their ability to interact with users through conversation. In this work we aim to evaluate their ability to complete multi-turn tasks and interact with external databases in the context of established task-oriented dialogue benchmarks. We show that for explicit belief state tracking, LLMs underperform compared to specialized task-specific models. Nevertheless, they show ability to guide the dialogue to successful ending if given correct slot values. Furthermore this ability improves with access to true belief state distribution or in-domain examples.