Showing cs.GTShow all
2 papers · 1 filter
cs.GT2026
Pluralistic Leaderboards
Nika Haghtalab, Ariel D. Procaccia, Han Shao +2
Recent leaderboard-based evaluations of large language models aggregate user feedback by fitting a Bradley--Terry model to pairwise comparisons, producing a single global ranking b…
cs.GT2026
Adaptive Contracts for Cost-Effective AI Delegation
Eden Saig, Tamar Garbuz, Ariel D. Procaccia +2
When organizations delegate text generation tasks to AI providers via pay-for-performance contracts, expected payments rise when evaluation is noisy. As evaluation methods become m…