大模型能靠结构模式读懂乱码句子，揭示其智能本质
The unreasonable effectiveness of pattern matching
- 用结构模式而非词汇语义理解乱码文本
- 在多数词被替换成无意义词时仍能准确还原语义
- 适合对模型推理机制感兴趣的读者
我们报告了大型语言模型（LLMs）惊人的能力：即使大多数或所有内容词被随机替换为无意义字符串（如将'He dwushed a ghanc zawk'翻译为'He dragged a spare chair'），模型仍能理解'Jabberwocky'语言。这一发现回应了关于大模型本质的争议：它们是语言模仿者、数据库，还是网络的模糊版本？模型从结构模式中恢复意义的能力，体现了模式匹配的非平凡有效性。模式匹配并非'真正智能'的替代品，而是其核心组成部分。
原文摘要 · Abstract (English)
We report on an astonishing ability of large language models (LLMs) to make sense of "Jabberwocky" language in which most or all content words have been randomly replaced by nonsense strings, e.g., translating "He dwushed a ghanc zawk" to "He dragged a spare chair". This result addresses ongoing controversies regarding how to best think of what LLMs are doing: are they a language mimic, a database, a blurry version of the Web? The ability of LLMs to recover meaning from structural patterns speaks to the unreasonable effectiveness of pattern-matching. Pattern-matching is not an alternative to "real" intelligence, but rather a key ingredient.
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。