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.
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys
Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback
An EcoSage Assistant: Towards Building A Multimodal Plant Care Dialogue Assistant
OmniDialog: An Omnipotent Pre-training Model for Task-Oriented Dialogue System
A Survey of Text Watermarking in the Era of Large Language Models
CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models
Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference
E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation
CMed-GPT: Prompt Tuning for Entity-Aware Chinese Medical Dialogue Generation
Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue
An Empirical Bayes Framework for Open-Domain Dialogue Generation
X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects
Context-dependent Instruction Tuning for Dialogue Response Generation
Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
PRODIGy: a PROfile-based DIalogue Generation dataset
Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation
Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation
NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation
PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain
MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control
Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses
Hexa: Self-Improving for Knowledge-Grounded Dialogue System
Towards human-like spoken dialogue generation between AI agents from written dialogue
MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation
Learning to Diversify Neural Text Generation via Degenerative Model
Improving Medical Dialogue Generation with Abstract Meaning Representations
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation
Hi Model, generating 'nice' instead of 'good' is not as bad as generating 'rice'! Towards Context and Semantic Infused Dialogue Generation Loss Function and Evaluation Metric
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.