English(EN) Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists

研究发现：开放权重模型会填充JSON提取列表

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

arXiv上发表的一项新研究调查了当Schema指定最少列表条目数时，开放权重语言模型如何处理JSON提取任务。研究人员发现，即使源文档中的项目少于此数量，模型也倾向于填充其输出列表以满足或超过此最小值。这种填充很难检测到，因为模型通常使用文档中的真实文本作为额外条目。标准的修复方法，例如指示可以接受更少的条目或提供“N/A”选项，只能部分缓解过度计数的问题。 AI

影响突出了当前开放权重模型在处理结构化数据方面一个微妙但可能很重要的缺陷，影响了提取任务的可靠性。

排序理由学术论文，详细介绍了模型行为的具体发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了模型行为的具体发现。[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: 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.CL TIER_1 English(EN) · Abhishek Barali, Aayush Paudel · 2026-10-23 04:00

Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists

arXiv:2610.30997v1 Announce Type: new Abstract: Extraction pipelines ask language models for JSON that follows a schema, and the schema can set a minimum number of list entries. We ask what models do when the document holds fewer items than that minimum. Under a preregistered pla…

本文如何被排名

报道来源 [1]

Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists

相关实体

相关话题