Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
A heatmap of OpinionQA scores showing how well each model reflects different U.S. political ideologies.
Source publication
There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To address this need, we present Collective Constitutional AI (CCAI): a multi-stage process for sourcing and inte...
Context in source publication
Context 1
... ran this to understand how public input from a representative sample of Americans might change an LM's propensity to reflect various American political ideologies. According to the results (Figure 5), the Public and Standard constitution models do not significantly differ in how well they reflect some U.S. political ideologies compared to others (along an axis from "Very Conservative" to "Very Liberal"). In other words, the relative representativeness of different political groups did not change measurably. ...
