Task-Oriented Dialogue Systems

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

22 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 131 papers with code (308 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• A User Simulator for Task-Completion Dialogues
  17 Dec 2016 10 repositories listed
  Then, one can train reinforcement learning agents in an online fashion as they interact with the simulator.
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
  15 Jan 2019 4 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge.
• MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation
  12 Oct 2020 3 repositories listed
  In this paper, we introduce MultiWOZ 2.
• Key-Value Retrieval Networks for Task-Oriented Dialogue
  15 May 2017 3 repositories listed
  Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.
• DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models
  4 Jan 2024 2 repositories listed
  We present DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems which facilitates systematic evaluations and comparisons between ToD systems using fine-tuning of Pretrained…
• In-Context Learning User Simulators for Task-Oriented Dialog Systems
  1 Jun 2023 2 repositories listed
  This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach.
• Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
  20 Feb 2023 2 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied.
• Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems
  2 Apr 2022 2 repositories listed Syntology ran 3 of 9 samples · 6 unverified · 2 pointer-only (licence)
  Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.
• DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context
  7 Jul 2021 2 repositories listed
  In this paper, we propose a multi-domain task-oriented dialogue system, called Dialogue System with Optimizing a Recurrent Action Policy using Efficient Context (DORA), that uses SL, with subsequently applied RL to…
• Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
  1 Apr 2021 2 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
• Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management
  29 Oct 2020 2 repositories listed
  We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents.
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System
  11 Jun 2020 2 repositories listed
  We test HDNO on MultiWoz 2.
• Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
  5 Jun 2020 2 repositories listed
  In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
• CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
  27 Feb 2020 2 repositories listed
  To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented…
• Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
  19 Nov 2019 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions.
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
  21 May 2019 2 repositories listed
  Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking.
• Global-Locally Self-Attentive Dialogue State Tracker
  19 May 2018 2 repositories listed Syntology ran 0 of 8 samples · 8 unverified · 3 pointer-only (licence)
  Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems.
• WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue
  2 Jun 2025 1 repository listed
  Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action.
• EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
  22 May 2025 1 repository listed
  However, sLLMs often struggle to maintain topic consistency in task-oriented dialogue systems, which is critical for scenarios such as service chatbots.
• LANID: LLM-assisted New Intent Discovery
  31 Mar 2025 1 repository listed
  New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones.
• Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues
  21 Jan 2025 1 repository listed
  Training task-oriented dialogue systems is both costly and time-consuming, due to the need for high-quality datasets encompassing diverse intents.
• Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
  26 Oct 2024 1 repository listed
  To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples.
• Confidence Estimation for LLM-Based Dialogue State Tracking
  15 Sep 2024 1 repository listed Syntology ran 10 of 12 samples · 2 unverified · 12 pointer-only (licence)
  We evaluate four methods for estimating confidence scores based on softmax, raw token scores, verbalized confidences, and a combination of these methods, using the area under the curve (AUC) metric to assess…
• Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation
  30 May 2024 1 repository listed
  The interaction between these two structures has not been considered for joint modeling and mutual learning.
• DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues
  16 May 2024 1 repository listed Syntology ran 2 of 3 samples · 1 unverified
  User Simulators play a pivotal role in training and evaluating task-oriented dialogue systems.
• Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
  23 Apr 2024 1 repository listed
  Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.
• Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
  23 Apr 2024 1 repository listed
  In our experiments, using graph-guided response simulations leads to significant improvements in intent classification, slot filling and response relevance compared to naive single-prompt simulated conversations.
• Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
  19 Apr 2024 1 repository listed
  Workers are more susceptible to user feedback on usefulness and interestingness compared to LLMs on interestingness and relevance.
• Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems
  15 Apr 2024 1 repository listed
  Using the first user utterance as context leads to consistent ratings, akin to those obtained using the entire dialogue, with significantly reduced annotation effort.
• JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset
  26 Mar 2024 1 repository listed
  In this study, towards the advancement of research and development of task-oriented dialogue systems in Japanese, we constructed JMultiWOZ, the first Japanese language large-scale multi-domain task-oriented dialogue…

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.