TY - CONF
T1 - Help me write a poem
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
AU - Chakrabarty, Tuhin
AU - Padmakumar, Vishakh
AU - He, He
N1 - Funding Information:
We would like to thank the anonymous reviewers for their helpful comments. We additionally also want to acknowledge all human authors who posted their work open-sourced on the websites we collected the data from. Tuhin is funded by Columbia Center of Artifical Intelligence & Technology (CAIT) and the Amazon Science Ph.D. Fellowship. This work is also supported by the Samsung Advanced Institute of Technology (Next Generation Deep Learning: From Pattern Recognition to AI), the National Science Foundation under Grant No. 1922658, and a gift from AWS AI.
Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - 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 user-generated 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 fine-tuned 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.
AB - 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 user-generated 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 fine-tuned 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.
UR - http://www.scopus.com/inward/record.url?scp=85144951001&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85144951001&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85144951001
SP - 6848
EP - 6863
Y2 - 7 December 2022 through 11 December 2022
ER -