模式匹配的不合理有效性
The unreasonable effectiveness of pattern matching
AI总结:
大型语言模型通过模式匹配有效理解随机替换实词的虚构文本,揭示了其在语言处理中的核心能力。
摘要:
我们报告了大型语言模型(LLMs)令人惊讶的能力,即能够理解其中大部分或全部实词已被随机替换为无意义字符串的“贾伯沃克”语言,例如将“He dwushed a ghanc zawk”翻译为“He dragged a spare chair”。这一结果回应了关于如何最好地理解LLMs在做什么的持续争议:它们是语言模仿者、数据库,还是模糊的网络版本?LLMs从结构模式中恢复意义的能力表明了模式匹配的不合理有效性。模式匹配不是“真实”智能的替代品,而是关键成分。
英文摘要:
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.
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。