SOTAVerified

Task-Oriented Dialogue Systems

Achieving a pre-defined task through a dialog.

Papers

Showing 1–10 of 308 papers

TitleStatusHype
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue DatasetCode4
TextBox 2.0: A Text Generation Library with Pre-trained Language ModelsCode3
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language ModelsCode2
WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented DialogueCode1
Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language ModelsCode1
JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue DatasetCode1
Task-Oriented Dialogue with In-Context LearningCode1
DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language ModelsCode1
Towards LLM-driven Dialogue State TrackingCode1
InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue SystemsCode1
Show:102550
← PrevPage 1 of 31Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1T5-3b(UnifiedSKG)Entity F170.07—Unverified
2COMETEntity F163.6—Unverified
3DF-NetEntity F162.7—Unverified
4DF-NetEntity F162.5—Unverified
5GLMPEntity F159.97—Unverified
6TTOSEntity F155.38—Unverified
7KB-retrieverEntity F153.7—Unverified
8DSREntity F151.9—Unverified
9KV Retrieval NetEntity F148—Unverified
10THPNEntity F137.8—Unverified
#ModelMetricClaimedVerifiedStatus
1T5METEOR0.33—Unverified
2BARTMETEOR0.09—Unverified
#ModelMetricClaimedVerifiedStatus
1BART (TextBox 2.0)BLEU-420.17—Unverified