Browse State-of-the-Art › Task-Oriented Dialogue Systems
Task-Oriented Dialogue Systems
131 papers with code · 4 benchmarks · 22 datasets archive 2025-07-28
Achieving a pre-defined task through a dialog.
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 308 · with a code link: 131 · where Syntology ran a sample: 17 (16 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (17 of 308 tagged: 16 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 4: papers 1 to 100 of 308, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
17 Dec 2016 10 repositories listedThen, one can train reinforcement learning agents in an online fashion as they interact with the simulator.
-
15 Jan 2019 4 repositories listed Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 2 pointer-only (licence)In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge.
-
12 Oct 2020 3 repositories listedIn this paper, we introduce MultiWOZ 2.
-
15 May 2017 3 repositories listedNeural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.
-
4 Jan 2024 2 repositories listedWe 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…
-
1 Jun 2023 2 repositories listedThis 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.
-
20 Feb 2023 2 repositories listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 1 pointer-only (licence)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.
-
2 Apr 2022 2 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 3 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.
-
7 Jul 2021 2 repositories listedIn 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…
-
1 Apr 2021 2 repositories listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
-
29 Oct 2020 2 repositories listedWe 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.
-
11 Jun 2020 2 repositories listedWe test HDNO on MultiWoz 2.
-
5 Jun 2020 2 repositories listedIn this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
-
27 Feb 2020 2 repositories listedTo 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…
-
19 Nov 2019 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 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.
-
21 May 2019 2 repositories listedOver-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking.
-
19 May 2018 2 repositories listed Syntology official (archive's flag): 4 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 7 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.
-
2 Jun 2025 1 repository listedTask-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action.
-
22 May 2025 1 repository listedHowever, sLLMs often struggle to maintain topic consistency in task-oriented dialogue systems, which is critical for scenarios such as service chatbots.
-
31 Mar 2025 1 repository listedNew Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones.
-
21 Jan 2025 1 repository listedTraining task-oriented dialogue systems is both costly and time-consuming, due to the need for high-quality datasets encompassing diverse intents.
-
26 Oct 2024 1 repository listedTo enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples.
-
15 Sep 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 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…
-
30 May 2024 1 repository listedThe interaction between these two structures has not been considered for joint modeling and mutual learning.
-
16 May 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)User Simulators play a pivotal role in training and evaluating task-oriented dialogue systems.
-
23 Apr 2024 1 repository listedIn 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.
-
23 Apr 2024 1 repository listedTraining task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e. g. a dialogue state and the system actions taken at each step.
-
19 Apr 2024 1 repository listedWorkers are more susceptible to user feedback on usefulness and interestingness compared to LLMs on interestingness and relevance.
-
15 Apr 2024 1 repository listedUsing the first user utterance as context leads to consistent ratings, akin to those obtained using the entire dialogue, with significantly reduced annotation effort.
-
26 Mar 2024 1 repository listedIn 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…
-
19 Feb 2024 1 repository listed
-
3 Feb 2024 1 repository listed
-
4 Dec 2023 1 repository listed
-
15 Nov 2023 1 repository listed
-
2 Nov 2023 1 repository listed
-
23 Oct 2023 1 repository listed
-
23 Oct 2023 1 repository listed
-
13 Oct 2023 1 repository listed
-
13 Oct 2023 1 repository listed
-
2 Oct 2023 1 repository listed
-
29 Jul 2023 1 repository listed
-
26 May 2023 1 repository listed
-
24 May 2023 1 repository listed
-
23 May 2023 1 repository listed
-
7 Mar 2023 1 repository listed
-
26 Dec 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
15 Dec 2022 1 repository listed
-
10 Dec 2022 1 repository listed
-
7 Nov 2022 1 repository listed
-
21 Oct 2022 1 repository listed
-
19 Oct 2022 1 repository listed
-
17 Oct 2022 1 repository listed
-
14 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
6 Sep 2022 1 repository listed
-
15 Aug 2022 1 repository listed
-
4 Aug 2022 1 repository listed
-
25 Jul 2022 1 repository listed
-
2 Jul 2022 1 repository listed
-
26 May 2022 1 repository listed
-
25 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples)
-
19 May 2022 1 repository listed
-
7 May 2022 1 repository listed
-
23 Apr 2022 1 repository listed
-
23 Mar 2022 1 repository listed
-
21 Mar 2022 1 repository listed
-
11 Mar 2022 1 repository listed
-
21 Jan 2022 1 repository listed
-
16 Jan 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
16 Nov 2021 1 repository listed
-
4 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
29 Oct 2021 1 repository listed
-
14 Oct 2021 1 repository listed
-
28 Sep 2021 1 repository listed
-
18 Sep 2021 1 repository listed
-
10 Sep 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
10 Jun 2021 1 repository listed
-
10 Jun 2021 1 repository listed
-
4 Jun 2021 1 repository listed
-
2 Jun 2021 1 repository listed
-
8 May 2021 1 repository listed
-
8 May 2021 1 repository listed
-
9 Apr 2021 1 repository listed
-
1 Apr 2021 1 repository listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
16 Feb 2021 1 repository listed
-
27 Jan 2021 1 repository listed
-
22 Jan 2021 1 repository listed
-
22 Jan 2021 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
31 Dec 2020 1 repository listed
-
22 Dec 2020 1 repository listed
-
20 Nov 2020 1 repository listed
-
18 Nov 2020 1 repository listed
-
3 Nov 2020 1 repository listed
-
Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training1 Nov 2020 1 repository listed
-
24 Oct 2020 1 repository listed
Syntology lines on 13 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections