English(EN) Distributions In, Distributions Out: The Case for Soft-Label Training

软标签训练通过使用完整的标注分布来提高分类器准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-31 04:00

研究人员提出了一种名为软标签训练的新型监督分类器训练方法，该方法利用标注者标签的完整分布，而不是单一的多数投票。这种方法对于具有内在歧义的任务特别有益，例如自然语言推理或礼貌检测。跨三个数据集的实验表明，软标签训练的准确性可与硬标签相媲美或超越硬标签，显著减少与标注者分布的偏差，并产生反映人类分歧的不确定性模型。 AI

影响这种方法可能导致在涉及主观或模糊人类判断的任务中，AI模型更加细致和准确。

排序理由该集群包含一篇详细介绍监督分类器新训练方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍监督分类器新训练方法的论文。[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, model release; 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: 48 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Agamdeep Singh, Ashish Tiwari, Hosein Hasanbeig, Priyanshu Gupta · 2026-07-31 04:00

分布进，分布出：软标签训练的理由

arXiv:2511.14117v2 Announce Type: replace Abstract: Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote. On tasks where annotator disagreement reflects genuine a…

本文如何被排名

报道来源 [1]

分布进，分布出：软标签训练的理由

相关实体

相关话题