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.
Further readings:
<span style="color:grey; opacity: 0.6">( Image credit: Adversarial Ranking for Language Generation )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
Flexible-length Text Infilling for Discrete Diffusion Models
The Safety Reminder: A Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models
TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications
SDialog: A Python Toolkit for Synthetic Dialogue Generation and Analysis
Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
The Diffusion Duality
VINCIE: Unlocking In-context Image Editing from Video
OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
Consistent Story Generation with Asymmetry Zigzag Sampling
Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective
HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration
Towards Secure and Private Language Models for Nuclear Power Plants
Adversarial Text Generation with Dynamic Contextual Perturbation
Evaluation empirique de la sécurisation et de l'alignement de ChatGPT et Gemini: analyse comparative des vulnérabilités par expérimentations de jailbreaks
ARGUS: Hallucination and Omission Evaluation in Video-LLMs
Improving Fairness of Large Language Models in Multi-document Summarization
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop
Proactive Assistant Dialogue Generation from Streaming Egocentric Videos
HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions
Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations
Controlling Summarization Length Through EOS Token Weighting
Do Large Language Models Judge Error Severity Like Humans?
Counterfactual reasoning: an analysis of in-context emergence
Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games
ConsistentChat: Building Skeleton-Guided Consistent Dialogues for Large Language Models from Scratch
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models
Backbone Augmented Training for Adaptations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.