LLM对话再流畅，也可能因本质模糊性而无真实理解
Large Language Models Understanding: an Inherent Ambiguity Barrier
- 通过思想实验揭示语言模型存在固有模糊性障碍
- 模型输出虽流畅，但无法确定其对话的真实语义
- 适合关注AI理解能力边界的研究者阅读
自大型语言模型（LLMs）出现以来，关于其是否能真正理解世界、把握对话意义的热烈讨论持续不断。支持与反对观点基于思想实验、人机对话案例、统计语言分析及哲学思考等提出。本文通过一个思想实验和半形式化推理，提出一种反论：语言模型面临一种固有的模糊性障碍，使其无法真正理解自身所生成对话的含义，即使其表达极为流畅。
原文摘要 · Abstract (English)
A lively ongoing debate is taking place, since the extraordinary emergence of Large Language Models (LLMs) with regards to their capability to understand the world and capture the meaning of the dialogues in which they are involved. Arguments and counter-arguments have been proposed based upon thought experiments, anecdotal conversations between LLMs and humans, statistical linguistic analysis, philosophical considerations, and more. In this brief paper we present a counter-argument based upon a thought experiment and semi-formal considerations leading to an inherent ambiguity barrier which prevents LLMs from having any understanding of what their amazingly fluent dialogues mean.
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。