聚合歧义消解系统

中文摘要 AI 辅助

自然语言任务可能会让遵循协议的评估者在收到相同声明信息时给出不同的判定结果，我们研究聚合歧义消解系统（ADSs）。给定一项任务和一个候选解决方案，每位评估者会对该解决方案是否应被接受投出二元票，系统则汇总有限评估面板的投票。目标是相对于明确声明的评估者参考实现协议可复现性，而非语义真值。我们区分固定有限普查、概率评估者总体及增长普查极限，因为它们的端点定律与保证不可互换。在总体设定下，我们利用有限样本估计有限面板与声明评估者总体达成相同决策的频率，针对分歧概率至多为选定容差的候选解决方案比例，我们给出一个下置信界，该计算分别考虑候选解决方案的抽样与评估者的抽样，此构造允许由共享评估者行引发的列间存在任意依赖，且在评估者层使用精确二项式区间，在生成器层使用精确单侧二项式反演。模拟将实现与已知总体覆盖率进行比对，并揭示功效限制。

英文摘要

Natural-language tasks can elicit different verdicts from protocol-following evaluators that receive the same declared information. We study aggregate disambiguation systems (ADSs). Given a task and a candidate solution, each evaluator casts a binary vote on whether the solution should be accepted, and the system aggregates the votes of a finite panel. The target is protocol reproducibility relative to an explicitly declared evaluator reference, not semantic truth. We separate fixed finite censuses, probabilistic evaluator populations, and growing-census limits, since their endpoint laws and guarantees are not interchangeable. In the population setting, we use finite samples to estimate how often a finite panel reaches the same decision as the declared evaluator population. We provide a lower confidence bound on the fraction of candidate solutions for which the disagreement probability is at most a chosen tolerance. The calculation accounts separately for sampling candidate solutions and sampling evaluators. The construction permits arbitrary dependence among columns induced by shared evaluator rows and uses exact binomial intervals at the evaluator layer and an exact one-sided binomial inversion at the generator layer. Simulations check the implementation against known population coverages and expose power limitations.

发表机构

• GenLayer Labs Research（GenLayer实验室研究院）

机构由 AI 辅助整理，请以论文原文为准。