arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.19301cs.CLcs.AI
收藏

超越将死:探索 AI 文本中的创造性瓶颈

Beyond checkmate: exploring the creative chokepoints in AI text

The Pennsylvania State University(宾夕法尼亚州立大学);Amazon(亚马逊公司)

Nafis Irtiza Tripto, Saranya Venkatraman, Mahjabin Nahar, Dongwon Lee

AI总结:

该研究借鉴国际象棋开局、中局、残局结构,比较人类与 LLM 文本在引言、正文、结论中的语言和风格差异,发现正文最利于检测。

摘要:

大型语言模型(LLM)的快速发展彻底改变了文本生成,但也引发了人们对潜在滥用的担忧,因此检测 LLM 生成文本(AI 文本)变得日益重要。以往工作主要关注识别 AI 文本并有效地将其“将死”,而本研究考察一个较少被探索的领域:刻画人类文本与 AI 文本在不同文本片段(引言、正文和结论)之间的细微差别。LLM 在跨文本片段融入语言创造性方面究竟表现出色还是存在不足,其结果将对它们作为人类有效创意助手的可行性和边界提供关键依据。通过类比国际象棋对局由开局、中局和残局组成的结构,我们分析特定片段的模式,以揭示最显著差异所在。尽管 AI 文本在正文片段因篇幅原因与人类写作高度相似,但更深入的分析表明,依赖语言连续流动的特征存在更高分歧,使正文成为检测信息量最大的片段。此外,人类文本在不同片段之间表现出更大的风格变化,为区分人类文本与 AI 文本提供了新视角。总体而言,我们的发现为人类—AI 文本差异提供了新的认识,并为更有效、更具可解释性的检测策略铺平道路。代码见 https://github.com/tripto03/chess_inspired_human_ai_text_distinction。

英文摘要:

The rapid advancement of Large Language Models (LLMs) has revolutionized text generation but also raised concerns about potential misuse, making detecting LLM-generated text (AI text) increasingly essential. While prior work has focused on identifying AI text and effectively checkmating it, our study investigates a less-explored territory: portraying the nuanced distinctions between human and AI texts across text segments (introduction, body, and conclusion). Whether LLMs excel or falter in incorporating linguistic ingenuity across text segments, the results will critically inform their viability and boundaries as effective creative assistants to humans. Through an analogy with the structure of chess games, comprising opening, middle, and end games, we analyze segment-specific patterns to reveal where the most striking differences lie. Although AI texts closely resemble human writing in the body segment due to its length, deeper analysis shows a higher divergence in features dependent on the continuous flow of language, making it the most informative segment for detection. Additionally, human texts exhibit greater stylistic variation across segments, offering a new lens for distinguishing them from AI. Overall, our findings provide fresh insights into human-AI text differences and pave the way for more effective and interpretable detection strategies. Codes available at https://github.com/tripto03/chess_inspired_human_ai_text_distinction.

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。

↑