发表机构
University of Nebraska-Lincoln; Harvard University（内布拉斯加大学林肯分校; 哈佛大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对众包竞赛中工人自主选择导致的参与不足和后悔问题，提出LLM增强的GRAF框架，通过LLMScore自动设计评分算法，在多种设置下实现接近最优且低后悔的结果。
AI 中文摘要
众包平台协调着庞大的在线工人群体，这些工人会策略性地选择参加哪些竞赛以及投入多少努力。这种自主选择可能导致重要竞赛参与者过少或投入努力不足，而工人也可能因参加竞赛后状况不如其他可选方案而后悔。我们研究平台如何利用Tullock竞赛中的自主选择（SSTC）向工人推荐竞赛，SSTC是一个两阶段模型，工人首先选择竞赛，然后在竞赛中竞争。我们引入GRAF，一种贪心多项式时间框架，通过根据得分向量对工人排序来构建自主选择结果，在SSTC的特殊情况下保证工人零后悔和平台最优性。由于在工人异质性下难以设计有效的排序，我们提出LLMScore，一种LLM驱动的进化框架，自动设计GRAF的评分算法。LLMScore解决了两个挑战：联合优化平台效用和工人满意度，以及在精确计算不可行时评估工人后悔。它仅在一个设置的小规模实例上训练，却能迁移到更大且结构不同的设置；此外，其输出是可读的代码，平台运营商可以检查和修改。在跨越四种设置的1,000个合成实例中，使用LLMScore的GRAF始终实现高质量、通常接近最优的结果，且工人后悔低，使平台和工人双方受益。
英文摘要
Crowdsourcing platforms coordinate large pools of online workers who strategically choose which contests to enter and how much effort to invest. This self-selection can leave important contests with too few participants or too little effort, while workers may regret entering contests that leave them worse off than available alternatives. We study how platforms can recommend contests to workers using self-selection in Tullock contests (SSTC), a two-stage model in which workers first choose contests and then compete within them. We introduce GRAF, a greedy polynomial-time framework that constructs self-selection outcomes by ordering workers according to a score vector, with guarantees of zero worker regret and platform optimality in special cases of SSTC. Because effective orderings are difficult to design under worker heterogeneity, we propose LLMScore, an LLM-driven evolutionary framework that automatically designs GRAF's scoring algorithm. LLMScore addresses two challenges: jointly optimizing platform utility and worker satisfaction, and evaluating worker regret when exact computation is intractable. Trained only on small instances of one setting, it transfers to larger and structurally different settings; moreover, its output is human-readable code that platform operators can inspect and modify. Across 1,000 synthetic instances spanning four settings, GRAF with LLMScore consistently achieves high-quality, often near-optimal, outcomes with low worker regret, benefiting both platforms and workers.
CommentsAccepted to HCOMP 2026
