SOTAVerified

Conditional Text Generation

The task of generating text according to some pre-specified conditioning (e.g. topic or sentiment or constraint)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 31–40 of 67 papers

TitleStatusHype
Token Manipulation Generative Adversarial Network for Text GenerationCode0
Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark RemedyCode0
Learning Implicit Text Generation via Feature Matching—0
FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training—0
Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection—0
Emotion-Conditioned Text Generation through Automatic Prompt Optimization—0
Discrete Copula Diffusion—0
MOPO: Multi-Objective Prompt Optimization for Affective Text Generation—0
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints—0
Discourse-Aware Prompt Design for Text Generation—0
Show:102550
← PrevPage 4 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-2-no-fine-tuningIgnored Constraint Error Rate28.2—Unverified
2GPT-2-fine-tuned-5-epochsIgnored Constraint Error Rate0.5—Unverified
3GPT-2-fine-tuned-20-epochsIgnored Constraint Error Rate0.3—Unverified
4GPT-2-with-filterIgnored Constraint Error Rate0—Unverified