Data to 7 Oct 2026

Are LLMs All You Need for Task-Oriented Dialogue?

arXiv 2304.06556 ↗First posted 13 Apr 2023cs.CLcited by 52

Not on the map. Why?

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.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

40 of 54 references.

References · 40

2017Attention Is All You Needcited by 59,932
2020Language Models are Few-Shot Learnerscited by 32,199
2022Training language models to follow instructions with human feedbackcited by 15,712
2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
2017Deep reinforcement learning from human preferencescited by 3,846
2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
2023A Survey of Large Language Modelscited by 2,537
2017Billion-scale similarity search with GPUscited by 2,477

28 more

2019Fine-Tuning Language Models from Human Preferencescited by 2,124
2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
2019Survey on Evaluation Methods for Dialogue Systemscited by 126
2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
2020A Sequence-to-Sequence Approach to Dialogue State Trackingcited by 43
2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
2017Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learningcited by 31
2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialogcited by 30
2018Zero-Shot Dialog Generation with Cross-Domain Latent Actionscited by 23
2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
2020Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluationcited by 19
2023Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systemscited by 19
2015Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Rerankingcited by 17
2018Multi-task learning for Joint Language Understanding and Dialogue State Trackingcited by 15
2021Robustness through Data Augmentation Loss Consistencycited by 8
2022AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialogcited by 8
2019Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networkscited by 3
2019MALA: Cross-Domain Dialogue Generation with Action Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 25; 2025: 18; 2026: 5.

52 papers.

Sort:

By area:

2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 102
2024Large Language Models Meet NLP: A Surveycited by 102
2024Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialoguecited by 64
2024BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filteringcited by 29
2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
2024DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialoguescited by 23
2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 17
2024Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applicationscited by 17
2025Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengescited by 12
2024Improving Tool Retrieval by Leveraging Large Language Models for Query Generationcited by 11

38 more

50 most cited of 52 All 52 (JSON)