English(EN) Challenges in annotations by humans and LLMs: A case study of evaluative language

研究发现：大型语言模型在复杂标注任务上可媲美训练有素的语言学家

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

一篇新发表在arXiv上的论文探讨了语言标注的挑战，比较了人类标注者和大型语言模型（LLMs）。研究人员分析了TED演讲稿中的评价性语言，重点关注了评价理论（Appraisal theory）的子范畴：情感（Affect）、判断（Judgement）和鉴赏（Appreciation）。研究发现，经过有效提示后，LLMs的表现与训练有素的语言学家相当，F1分数达到0.77，并且在训练方面优于语言学家。 AI

影响 LLMs在辅助复杂的标注任务方面展现出潜力，有望加速数字人文和语言学领域的研究。

排序理由该集群包含一篇详细介绍LLM能力研究的学术论文。[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: 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LLM能力研究的学术论文。[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, 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: 69 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.CL TIER_1 English(EN) · Mirela Imamovic, Aenne Cecilia Kristine Knierim, Khushi Pitroda, Ekaterina Lapshinova-Koltunski · 2026-07-31 04:00

人类和LLM标注的挑战：评估语言的案例研究

arXiv:2607.28119v1 Announce Type: new Abstract: In this paper, we draw a comparison between linguists in training, a trained linguist, and annotations generated by large language models (LLMs) to find out if they struggle with complex linguistic phenomena in a similar way. For th…

本文如何被排名

报道来源 [1]

人类和LLM标注的挑战：评估语言的案例研究

相关实体

相关话题