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 41–50 of 67 papers

TitleStatusHype
On the Anatomy of Latent-variable Generative Models for Conditional Text Generation—0
Discourse-Aware Soft Prompting for Text Generation—0
Transfer Reward Learning for Policy Gradient-Based Text Generation—0
Conditional Variational Autoencoder for Neural Machine Translation—0
Pretraining for Conditional Generation with Pseudo Self Attention—0
Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation—0
Realistic simulation of users for IT systems in cyber ranges—0
Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models—0
DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion—0
DiffuDetox: A Mixed Diffusion Model for Text Detoxification—0
Show:102550
← PrevPage 5 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