大模型在严重字符错乱下仍能准确理解文本，揭示其底层鲁棒性。
Understanding the Ability of LLMs to Handle Character-Level Perturbation
- 测试三种字符级扰动：拼写错误、字符乱序、插入隐形字符。
- 即使字符乱序或隐形字符超可见字符数倍，模型仍保持显著性能。
- 发现模型具备隐式与显式去除扰动的机制，适合安全与可信应用研究。
本文研究当代大语言模型（LLMs）对频繁字符级扰动的鲁棒性。实验考察三类扰动：单词内大量拼写错误、单词内字符随机打乱、文本中插入大量隐形字符。令人惊讶的是，即使在严重扰动下——如将几乎所有单词字符彻底打乱导致人类几乎无法阅读，或插入的隐形字符数量为可见字符的数倍作为噪声——许多大模型仍保持显著性能。我们探究其背后原因，发现大模型对混乱分词和碎片化分词具有极强鲁棒性。进一步分析模型如何识别并纠正扰动以正确理解文本，揭示了字符级扰动下的隐式与显式消除机制。研究结果有助于揭示大模型的内在架构优势，揭示潜在滥用风险，并指导其在多样化应用场景中的可靠部署。
原文摘要 · Abstract (English)
This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturbations including introducing numerous typos within words, shuffling the characters in each word, and inserting a large number of invisible characters into the text. Surprisingly, even under severe perturbation, such as shuffling nearly all words character-wise to produce text that is almost unreadable to humans, or inserting invisible characters which are several times more than the visible ones as noise, many LLMs still maintain notable performance. We explore the underlying causes of this robustness and find that LLMs exhibit remarkable resilience to chaotic segmentation and fragmented tokenization. Furthermore, we examine the mechanisms by which LLMs remove perturbations to correctly comprehend text, including both implicit and explicit mechanisms for character-level perturbation. We hope that our findings on the low-level robustness of LLMs will unveil their inherent architectural strengths, reveal the potential risks of their misuse, and inform the reliable deployment of LLMs across diverse application scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。