Recent work in training large language models (LLMs) to follow natural language
instructions has opened up exciting opportunities for natural language interface
design. Building on the prior success of LLMs in the realm of computer-assisted
creativity, we aim to study if LLMs can improve the quality of usergenerated content
through collaboration. We present CoPoet, a collaborative poetry writing system.
In contrast to auto-completing a user’s text, CoPoet is controlled by user instructions
that specify the attributes of the desired text, such as Write a sentence about "love"
or Write a sentence ending in "fly". The core component of our system is a language
model finetuned on a diverse collection of instructions for poetry writing. Our model is not
only competitive with publicly available LLMs trained on instructions (InstructGPT), but is
also capable of satisfying unseen compositional instructions. A study with 15 qualified
crowdworkers shows that users successfully write poems with CoPoet on diverse topics ranging from
Monarchy to Climate change. Further, the collaboratively written poems are preferred by third-party
evaluators over those written without the system
Poem entitled `Glass Ceilings' written in collaboration with CoPoet
Demo Video
Paper
If you use our dataset or evaluation platform, please cite:
@article{chakrabarty2022help,
title={Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing},
author={Chakrabarty, Tuhin and Padmakumar, Vishakh and He, He},
journal={arXiv preprint arXiv:2210.13669},
year={2022}
}
Contact
If you have any questions or comments about this work, please contact Tuhin or Vishakh.
