Papers with Code 아카이브
Dialogue Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 13
- 보존된 평가 기록
- 20
Dialogue generation is the task of "understanding" natural language inputs - within natural language processing in order to produce output. The systems are usually intended for conversing with humans, for instance back and forth dialogue with a conversation agent like a chatbot. Some example benchmarks for this task (see others such as Natural Language Understanding) include FusedChat and Ubuntu DIalogue Corpus (UDC). Models can be evaluated via metrics such as BLEU, ROUGE, and METEOR albeit with challenges in terms of weak correlation with human judgement, that may be addressed by new ones like UnSupervised and Reference-free (USR) and Metric for automatic Unreferenced dialog evaluation (MaUde).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting
A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue
Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations
Concept Matching with Agent for Out-of-Distribution Detection
M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions
Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation
A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks
Research on emotionally intelligent dialogue generation based on automatic dialogue system
Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation
Impact of Preference Noise on the Alignment Performance of Generative Language Models
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation
PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models
Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation
BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation
Empowering Segmentation Ability to Multi-modal Large Language Models
StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation
MedKP: Medical Dialogue with Knowledge Enhancement and Clinical Pathway Encoding
Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue
MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
Exploiting Emotion-Semantic Correlations for Empathetic Response Generation
Evaluating Very Long-Term Conversational Memory of LLM Agents
M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement
Crafting a Good Prompt or Providing Exemplary Dialogues? A Study of In-Context Learning for Persona-based Dialogue Generation
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.