arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2506.00784cs.CL

研究边疆:跨研究文化中的写作分析

Research Borderlands: Analysing Writing Across Research Cultures

Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所);Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校Siebel计算与数据科学学院);Pioneer Centre for AI, University of Copenhagen(哥本哈根大学先锋人工智能中心);Allen Institute for Artificial Intelligence (Ai2)(人工智能研究院)

Shaily Bhatt, Tal August, Maria Antoniak

AI总结:

本文通过跨文化访谈,揭示研究文化中的语言规范,并评估LLM的文化适应能力,强调人类中心方法在测量文化规范中的有效性。

摘要:

提升语言技术的文化能力至关重要。然而,大多数最新研究很少与所研究的社区互动,而是依赖合成设置和不完美的文化代理。本文采用以人类为中心的方法,发现并测量基于语言的文化规范以及LLM的文化能力。我们专注于一种文化——研究文化,以及一种任务——在不同研究文化中适应写作。通过与跨学科研究者进行访谈,这些专家擅长在不同文化间转换,我们创建了结构、风格、修辞和引用规范的框架,这些规范在不同研究文化中有所不同。我们通过一组计算度量来操作这些特征,并用于(a)大规模揭示人类写作研究论文中的潜在文化规范;以及(b)突出LLM缺乏文化能力,以及其倾向于同质化写作的倾向。总体而言,我们的工作展示了以人类为中心的方法在测量人类写作和LLM生成文本中的文化规范的有效性。

英文摘要:

Improving cultural competence of language technologies is important. However most recent works rarely engage with the communities they study, and instead rely on synthetic setups and imperfect proxies of culture. In this work, we take a human-centered approach to discover and measure language-based cultural norms, and cultural competence of LLMs. We focus on a single kind of culture, research cultures, and a single task, adapting writing across research cultures. Through a set of interviews with interdisciplinary researchers, who are experts at moving between cultures, we create a framework of structural, stylistic, rhetorical, and citational norms that vary across research cultures. We operationalise these features with a suite of computational metrics and use them for (a) surfacing latent cultural norms in human-written research papers at scale; and (b) highlighting the lack of cultural competence of LLMs, and their tendency to homogenise writing. Overall, our work illustrates the efficacy of a human-centered approach to measuring cultural norms in human-written and LLM-generated texts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑