Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grunde-McLaughlin, Madeleine, Lam, Michelle S., Krishna, Ranjay, Weld, Daniel S., Heer, Jeffrey
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915048444657664
author Grunde-McLaughlin, Madeleine
Lam, Michelle S.
Krishna, Ranjay
Weld, Daniel S.
Heer, Jeffrey
author_facet Grunde-McLaughlin, Madeleine
Lam, Michelle S.
Krishna, Ranjay
Weld, Daniel S.
Heer, Jeffrey
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11681
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
Grunde-McLaughlin, Madeleine
Lam, Michelle S.
Krishna, Ranjay
Weld, Daniel S.
Heer, Jeffrey
Human-Computer Interaction
Artificial Intelligence
Computation and Language
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.
title Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2312.11681