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.

Dialogue Generation

논문

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation

Intent-Aware Dialogue Generation and Multi-Task Contrastive Learning for Multi-Turn Intent Classification

Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey

Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation

Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue

An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation

Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation

PersoBench: Benchmarking Personalized Response Generation in Large Language Models

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

A Two-Stage Proactive Dialogue Generator for Efficient Clinical Information Collection Using Large Language Model

DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications

MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation

LLMR: Knowledge Distillation with a Large Language Model-Induced Reward

ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

UPCS: Unbiased Persona Construction for Dialogue Generation

User-Specific Dialogue Generation with User Profile-Aware Pre-Training Model and Parameter-Efficient Fine-Tuning

Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies

Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search

An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation

ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language

Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation

Synthetic Patient-Physician Dialogue Generation from Clinical Notes Using LLM

Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies

Self-Emotion Blended Dialogue Generation in Social Simulation Agents

What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling

A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation

CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding

Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model

MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space

Learning Retrieval Augmentation for Personalized Dialogue Generation

Selective Prompting Tuning for Personalized Conversations with LLMs