Phraselette: A Poet's Procedural Palette
Alex Calderwood, John Joon Young Chung, Yuqian Sun, Melissa Roemmele, Max Kreminski
TL;DR
This paper argues that current automated writing tools impose a normative ground misaligned with writerly values and proposes Phraselette as a material writing support interface that prioritizes textual material and interpretive flexibility over full automation. By introducing contingent Wells (Words, Thesaurus, Reader, Context, Sound, Dictionary) and a modular, extensible design, Phraselette enables experimental poets to search for words and phrases at chosen sites, while exposing language-model affordances in service of writerly practices. An extended study with 10 published poets shows the approach supports revision, conceptual discovery, and multi-Well workflows without sacrificing ownership, though it raises practical issues such as speed, bugs, and some distraction. The work demonstrates a viable design path for writer-aligned AI writing tools, contributing both a concrete system and a theoretical framework for material writing and the normative ground of text generation.
Abstract
According to the recently introduced theory of artistic support tools, creativity support tools exert normative influences over artistic production, instantiating a normative ground that shapes both the process and product of artistic expression. We argue that the normative ground of most existing automated writing tools is misaligned with writerly values and identify a potential alternative frame-material writing support-for experimental poetry tools that flexibly support the finding, processing, transforming, and shaping of text(s). Based on this frame, we introduce Phraselette, an artistic material writing support interface that helps experimental poets search for words and phrases. To provide material writing support, Phraselette is designed to counter the dominant mode of automated writing tools, while offering language model affordances in line with writerly values. We further report on an extended expert evaluation involving 10 published poets that indicates support for both our framing of material writing support and for Phraselette itself.
