DATG

awesome-LLM-controlled-constrained-generation

The code implementation of the EMNLP2022 paper: DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation

Implementing Simulation-guided Beam Search for text generation. Idea already proposed in Choo et al for Neural Combinatorial Optimization. In this repo, we use the technique for Controllable Text Generation.

Generate Russian text using GPT model given LaBSE text embedding vector

Controllable text generation project using different approaches