Papers with Code 아카이브

Text Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 25
평가표: 155
보존된 평가 기록: 54

Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.

Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Text Generation

논문

Linear-time Minimum Bayes Risk Decoding with Reference Aggregation

Cataloguing Hugging Face Models to Software Engineering Activities: Automation and Findings

Emotional Support with LLM-based Empathetic Dialogue Generation

Making Language Model a Hierarchical Classifier and Generator

Mitigating Object Hallucinations via Sentence-Level Early Intervention

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models

FIFA: Unified Faithfulness Evaluation Framework for Text-to-Video and Video-to-Text Generation

CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs

OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation

Hierarchical Interaction Summarization and Contrastive Prompting for Explainable Recommendations

Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering

The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems

CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs

Compressed and Smooth Latent Space for Text Diffusion Modeling

Cat and Mouse -- Can Fake Text Generation Outpace Detector Systems?

Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

Shape2Animal: Creative Animal Generation from Natural Silhouettes

Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer

Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes

Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation

LettinGo: Explore User Profile Generation for Recommendation System

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

OmniGen2: Exploration to Advanced Multimodal Generation

Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation

StoryWriter: A Multi-Agent Framework for Long Story Generation

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models

GenerationPrograms: Fine-grained Attribution with Executable Programs

Human-Centered Editable Speech-to-Sign-Language Generation via Streaming Conformer-Transformer and Resampling Hook