Contribution to the handbook
Supporting · Assessed 2026-10-28
The urban-planning paired-comparison method provides relevant background on one way to elicit and summarize policy preferences. The evidence describes the adaptation and its study-specific comparisons, while also limiting what those comparisons establish. It informs possible participation and testing approaches but does not itself specify a governance mechanism.
Does this challenge the goal?
In-scope gap
The question concerns a possible method for collecting and mapping policy preferences, within the existing citizen-serving and testing goals; it does not challenge those goals.
The study’s adaptation of an earlier method is not evidence that the method is suitable for civic decisions or for binding governance.
Why this category?
- Background on a possible preference-elicitation method and its limits
The described method and results come from the same study source. The evidence does not establish suitability for other settings, representativeness, or how the resulting preferences would affect decisions.
This is an AI assessment of contribution to the goal, separate from whether the question has an answer.
- What earlier method inspired the study’s design?
- Why the experiment used pairs
- Group preferences were consistent on retest
- The data used in the comparison
- A method adapted from urban planning
- Anonymous pairwise comparisons
- Summarizing group preferences with win rates
- The volunteer policy data
- Comparing sample and full-sample patterns
Making and interpreting laws →
Tests, stop conditions and unresolved work →
Read the exploration goalNew evidence is being assessed. Any answer below is provisional; parts whose evidence changed or was withdrawn are withheld.
Identify the urban-planning paired-comparison method and how the study adapts its use of choices to map preferences.
What we can say so far
The study was inspired by paired comparison from urban planning: people compare options, and models use those choices to create preference maps. It adapts this approach by collecting pairwise choices between policy proposals and summarizing those choices to map group preferences.
What remains open
No material gap is recorded within this part’s current scope.
Conditions and limits
- The authors present the urban-planning method as an analogy; this does not establish that the two applications produce identical results.
Evidence and related ideas
Supporting evidence, qualifications and context play different roles in this answer.
supports
A method adapted from urban planning The study adapts a paired-comparison approach from urban planning, where people compare options and models use those choices to create detailed preference maps.
Directly names the urban-planning paired-comparison approach and its use of choices to create preference maps.
Large Language Models (LLMs) as Agents for Augmented Democracy
Read full source: Large Language Models (LLMs) as Agents for Augmented Democracy (opens in a new tab) ↗Read source discussion: Large Language Models (LLMs) as Agents for Augmented Democracy →
context
Group preferences were consistent on retest The authors estimate 95.38% test-retest reliability for the group’s preferences in the full participant sample. They say this is consistent with earlier paired-comparison work, where rankings tended to converge after about 30 to 40 choices per participant.
Provides context about earlier paired-comparison work, but is not needed to identify the method or its adaptation.
Large Language Models (LLMs) as Agents for Augmented Democracy
Read full source: Large Language Models (LLMs) as Agents for Augmented Democracy (opens in a new tab) ↗