Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
ACM Transactions on Computer-Human Interaction · 30.06.2025 · 32 (3) · 1-57
DOI: 10.1145/3716134 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Computer-Human Interaction, online erschienen am 14.06.2025. Verfasst von Madeleine Grunde-McLaughlin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 177 Literaturangaben. Gefördert von: National Science Foundation, Office of Naval Research, Allen Institute for Artificial Intelligence.
Abstract (Originalsprache)
LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into smaller tasks for human crowdworkers. Chains address LLM errors analogously to the way crowdsourcing workflows address human error. To characterize opportunities for LLM chaining, we survey 107 papers across the crowdsourcing and chaining literature to construct a design space for chain development. The design space covers a designer’s objectives and the tactics used to build workflows. We then surface strategies that mediate how workflows use tactics to achieve objectives. To explore how techniques from crowdsourcing may apply to chaining, we adapt crowdsourcing workflows to implement LLM chains across three case studies: creating a taxonomy, shortening text, and writing a short story. From the design space and our case studies, we identify takeaways for effective chain design and raise implications for future research and development.
Förderung
- National Science Foundation
- Office of Naval Research
- Allen Institute for Artificial Intelligence
Zitieren
APA
Grunde-McLaughlin, M., Lam, M. S., Krishna, R., Weld, D. S., & Heer, J. (2025). Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows. ACM Transactions on Computer-Human Interaction, 32(3), 1-57. https://doi.org/10.1145/3716134
Vancouver
Grunde-McLaughlin M, Lam MS, Krishna R, Weld DS, Heer J. Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows. ACM Transactions on Computer-Human Interaction. 2025;32(3):1-57. doi:10.1145/3716134
BibTeX
@article{GrundeMcLaughlin2025,
author = {Grunde-McLaughlin, Madeleine and Lam, Michelle S. and Krishna, Ranjay and Weld, Daniel S. and Heer, Jeffrey},
title = {Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows},
journal = {ACM Transactions on Computer-Human Interaction},
year = {2025},
volume = {32},
number = {3},
pages = {1--57},
doi = {10.1145/3716134}
}
EUVIMED