English(EN) A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral

新算法学习纠正在线延迟系统中的专家答案

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员开发了一种名为ORUCB的新在线学习算法，旨在改进延迟系统中专家答案的纠正。该算法解决了专家早期回答不准确会阻碍有价值查询的挑战。ORUCB汇集了共享和专家特定的多项式响应，使用累积误差的界限来校准置信度加权风险回归和探索。这使得系统能够更好地决定购买哪些答案，在特定条件下实现了O(sqrt(T log(T+1)))的伪遗憾。四个测试流上的实证结果表明，与七种不纠正答案的基线方法相比，ORUCB策略的包含费用成本更低。 AI

影响这项研究可能带来更高效、更准确的AI系统，这些系统能够从专家输入中学习和纠正，从而在复杂环境中改进决策。

排序理由学术论文，详细介绍了一种用于在线学习和专家纠正的新算法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

arXiv

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 7 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种用于在线学习和专家纠正的新算法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi · 2026-10-07 04:00

提问不等于承诺：学习纠正在线延迟中的专家答案

arXiv:2610.07084v1 Announce Type: cross Abstract: An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that f…

本文如何被排名

报道来源 [1]

提问不等于承诺：学习纠正在线延迟中的专家答案

相关实体

相关话题