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 1–10 of 67 papers

TitleStatusHype
MEDITRON-70B: Scaling Medical Pretraining for Large Language ModelsCode4
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and DatasetCode2
LOCOST: State-Space Models for Long Document Abstractive SummarizationCode1
GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and AugmentationCode1
Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationCode1
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in BanglaCode1
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text GenerationCode1
AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language ModelingCode1
Data-to-text Generation by Splicing Together Nearest NeighborsCode1
Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute ManipulationCode1
Show:102550
← PrevPage 1 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