Pairwise Ranking

Pairwise ranking studies how to recover useful orderings from judgments such as which of two models, answers, or products is better. Common approaches include Bradley–Terry and Elo models, spectral methods, and active learning that selects informative comparisons; neural pairwise and listwise reward models extend these ideas to quality assessment and preference optimization. Applications include recommender systems, human-in-the-loop annotation, and LLM leaderboards evaluated with paired benchmarks. A central challenge is that comparisons can be noisy, biased, or heterogeneous, so cycles and close rankings may make a single global order unstable or statistically unresolved.