Taxonomy / Deliberative aggregation / Voting among many judges at evaluation time
Voting among many judges at evaluation time
Rather than building the aggregation into training, these systems gather many evaluative signals after the fact and combine them with a voting rule instead of an average. Several models from different families, or one compact reward model fitted per annotator, each score the candidate outputs and vote; the same move treats existing benchmark and tournament results as ballots and searches for the ranking of agents that contradicts the fewest of them. Because the voters live at evaluation time, who votes is a knob that can be turned without retraining anything — which is what separates this from rewriting the objective.
Scroll the diagram sideways to see all of it.
Papers
Soft Condorcet Optimization for Ranking of General Agents
Marc Lanctot et al., Oct 2024arXiv:2411.00119MethodBuilt
Ranks agents by treating benchmark and tournament results as votes and searching for the ranking that mispredicts the fewest pairwise comparisons, landing on average 0 to 0.043 in normalized Kendall-tau from the optimal ranking across 865 PrefLib preference profiles and giving the best approximation to the optimal ranking on held-out test sets from 31,049 games of seven-player Diplomacy played by 52,958 people.
Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy
Rachel Freedman, May 2026arXiv:2605.01642MethodPartial
Learns a compact reward model per annotator by low-rank decomposition over a shared reward basis, has those models vote as a jury over candidate outputs under a social-choice rule, and adapts the jury over time by fitting new annotator weights on the fixed bases as values shift; a proof-of-concept on the PRISM dataset with simulated historical annotators finds that jury composition and the choice of voting rule can substantially affect outcomes where jury preferences are heterogeneous.
Measured, not built
Instruments that measure this rather than instantiating it. This map is a map of methods, so they are indexed here but counted nowhere on the grid.