神经作者归属：对大型语言模型的文体学分析
Neural Authorship Attribution: Stylometric Analysis on Large Language Models
AI总结：
本文针对专有与开源 LLM 生成文本的来源识别问题，结合词汇、句法和结构文体特征增强预训练分类器，并通过实证比较揭示不同模型的写作签名。
摘要：
诸如 GPT-4、PaLM 和 Llama 之类的大型语言模型（LLM）显著推动了 AI 生成文本的产生。随着人们对其潜在滥用的担忧日益加剧，AI 生成文本取证已成为迫切需求。神经作者归属是一项取证工作，旨在将 AI 生成文本追溯至生成它的原始 LLM。LLM 领域可分为两大主要类别：专有模型和开源模型。在本研究中，我们深入考察这些新兴的 LLM 类别，重点关注神经作者归属中的细微差异。为增进理解，我们对 LLM 的写作特征进行实证分析，突出专有模型与开源模型之间的差异，并仔细审查各组内部的变化。通过整合语言在词汇、句法和结构层面的文体学特征，我们探索这些特征产生可解释结果并增强神经作者归属中所使用的基于预训练语言模型的分类器的潜力。我们基于一系列最先进 LLM 的研究结果，为神经作者归属提供了实证洞见，并为未来旨在减轻 AI 生成虚假信息所造成威胁的研究铺平道路。
英文摘要：
Large language models (LLMs) such as GPT-4, PaLM, and Llama have significantly propelled the generation of AI-crafted text. With rising concerns about their potential misuse, there is a pressing need for AI-generated-text forensics. Neural authorship attribution is a forensic effort, seeking to trace AI-generated text back to its originating LLM. The LLM landscape can be divided into two primary categories: proprietary and open-source. In this work, we delve into these emerging categories of LLMs, focusing on the nuances of neural authorship attribution. To enrich our understanding, we carry out an empirical analysis of LLM writing signatures, highlighting the contrasts between proprietary and open-source models, and scrutinizing variations within each group. By integrating stylometric features across lexical, syntactic, and structural aspects of language, we explore their potential to yield interpretable results and augment pre-trained language model-based classifiers utilized in neural authorship attribution. Our findings, based on a range of state-of-the-art LLMs, provide empirical insights into neural authorship attribution, paving the way for future investigations aimed at mitigating the threats posed by AI-generated misinformation.
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。
