REVIEW 3 cited by
Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
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.
Forward citations
Cited by 3 Pith papers
-
Steering Semantic Data Processing With DocWrangler
An IDE for LLM-powered text data processing, with user studies showing that people convert open-ended operations into structured classifiers and use vague prompts to explore their data.
-
Linting is People! Exploring the Potential of Human Computation as a Sociotechnical Linter of Data Visualizations
Crowd-sourced Community Notes on social media can function as a sociotechnical linter for data visualizations, extending the linting metaphor from code to human computation.
-
Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition
A multi-step transparent AI workflow improves appropriate reliance only for users who already decide intermediate sub-facts accurately; otherwise it causes under-reliance.
Discussion (0). Continue with ORCID to comment.