arXiv cs.CL· Niharika Hegde, Subarnaduti Paul, Lars-Joel Frey, Manuel Brack, Kristian Kersting, Martin Mundt, Patrick Schramowski·· 2 天前AI 评分22
Chronoberg：面向语言模型分析的 250 年历时语料库与时间情感词典
Chronoberg: A 250-Year Diachronic Corpus with Temporal Affective Lexicons for Language Model Analysis
AI 导读
研究者发布 Chronoberg，一个取自 Project Gutenberg、覆盖 250 年英文书籍的时序结构化语料库，并附带时间标注与 Valence-Arousal-Dominance 情感词典。基于该词典的分析显示，现代 LLM 工具难以处理词义随时间发生的历时变化，在情感语境化和歧视性语言检测上表现不佳。Chronoberg 已在 HuggingFace 公开，代码同步开放。
正文 · 原文
Abstract:Large language models (LLMs) excel at operating at scale by leveraging social media and data crawled from the web. Whereas existing corpora are diverse, their frequent lack of long-term temporal structure may however limit an LLM's ability to contextualize semantic and normative evolution of language and to capture diachronic variation. To support the latter, we introduce Chronoberg, a temporally structured corpus of English book texts spanning 250 years, curated from Project Gutenberg and enriched with a variety of temporal annotations. First, the edited nature of books enables us to quantify lexical semantic change through time-sensitive Valence-Arousal-Dominance analysis and to support historically-grounded interpretation. With the lexicons at hand, we demonstrate a need for modern LLM-based tools to better situate their contextualization of sentiment and detection of discriminatory language across various time-periods. In fact, we show how these tools struggle with diachronic shifts in meaning, emphasizing the need for temporally aware training and evaluation pipelines, and positioning Chronoberg as a scalable resource for respective studies. Disclaimer: This paper includes language and display of samples that could be offensive to readers. Open Access: Chronoberg is available publicly on HuggingFace at this https URL. Code is available at this https URL.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2509.22360 [cs.CL] |
| (or arXiv:2509.22360v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2509.22360 arXiv-issued DOI via DataCite |
Submission history
From: Subarnaduti Paul [view email]
[v1]
Fri, 26 Sep 2025 13:56:16 UTC (4,108 KB)
[v2]
Thu, 10 Sep 2026 09:49:02 UTC (598 KB)
[v3]
Thu, 15 Oct 2026 12:29:36 UTC (598 KB)
来源：arXiv cs.CL · arxiv.org