SOTAVerified

Response Generation

A task where an agent should play the $DE$ role and generate a text to respond to a $P$ message.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 914 papers

TitleStatusHype
Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue SystemCode1
Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine MisinformationCode1
Guiding Large Language Models via Directional Stimulus PromptingCode1
Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service SupportCode1
Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue SystemsCode1
CARE: Causality Reasoning for Empathetic Responses by Conditional Graph GenerationCode1
ComFact: A Benchmark for Linking Contextual Commonsense KnowledgeCode1
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge SelectionCode1
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained DecodingCode1
AARGH! End-to-end Retrieval-Generation for Task-Oriented DialogCode1
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response GenerationCode1
INSCIT: Information-Seeking Conversations with Mixed-Initiative InteractionsCode1
Joint Generator-Ranker Learning for Natural Language GenerationCode1
ProsocialDialog: A Prosocial Backbone for Conversational AgentsCode1
KETOD: Knowledge-Enriched Task-Oriented DialogueCode1
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response GenerationCode1
HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party ConversationsCode1
Structure Extraction in Task-Oriented Dialogues with Slot ClusteringCode1
Contrast and Generation Make BART a Good Dialogue Emotion RecognizerCode1
Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta InformationCode1
Don’t be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue SystemCode1
A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue SystemsCode1
A Large-Scale Dataset for Empathetic Response GenerationCode1
Few-Shot Bot: Prompt-Based Learning for Dialogue SystemsCode1
Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response GenerationCode1
Show:102550
← PrevPage 4 of 37Next →
All datasetsSIMMC2.0ArgSciChatMMConv

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaCEBLEU34.1—Unverified
2BART-largeBLEU33.1—Unverified
3BART-baseBLEU29.4—Unverified
4MTNBLEU21.7—Unverified
5GPT-2BLEU19.2—Unverified
#ModelMetricClaimedVerifiedStatus
1LED(Q,F)Message-F119.54—Unverified
2LED(Q,P,H)Message-F116.14—Unverified
3LED(Q,P)Message-F114.25—Unverified
#ModelMetricClaimedVerifiedStatus
1PaCEBLEU22—Unverified
2SimpleTODBLEU20.3—Unverified