English(EN) CALICO: A Human-Centered, Codebook-Aligned System for Annotation

CALICO系统通过可编辑提示和新优化器增强LLM标注

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员推出CALICO，一个旨在改进大型语言模型基于代码本的标注过程的新系统。CALICO将提示视为可编辑和可优化的产物，使领域专家能够更好地理解和纠正模型行为。该系统集成了各种优化技术，包括一种名为ReflectAgent的新型基于反射的优化器，并在不同标注者之间显著提高了标注性能。 AI

影响增强了基于LLM的标注的可靠性和可审计性，可能提高在此类数据上训练的AI模型的质量。

排序理由该条目描述了在arXiv研究论文中提出的一种新的标注系统和方法。 [lever_c_demoted from research: ic=1 ai=1.0]

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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了在arXiv研究论文中提出的一种新的标注系统和方法。 [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, product; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Boqin Yuan, Xiaoyi Gu, Fiona Li, Chang Wan, Angel Hsing-Chi Hwang, Jieyu Zhao · 2026-09-15 04:00

CALICO：一个以人为本、代码本对齐的标注系统

arXiv:2609.14726v1 Announce Type: cross Abstract: Large language models are increasingly used to scale codebook-based annotation in scientific research, but existing workflows provide limited support for translating domain experts' codebooks into reliable, revisable, and auditabl…