arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.10684cs.CLcs.AI
收藏

语言模型很难理解我们

Language Models Understand Us, Poorly

University of Washington(华盛顿大学)

Jared Moore

摘要:

有些人声称语言模型理解我们。为了澄清,我调查了人类语言理解的三种观点:映射,可靠性和表征。我认为,虽然行为的可靠性是必要的理解,内部表示是足够的,他们爬上正确的山。我回顾了最先进的语言和多模态模型:它们受到形式规范不足的实用性挑战。我质疑扩展范式:资源的限制可能会阻止扩展模型接近理解。最后,我描述了作为表征如何推进理解科学。我们需要探索模型内部的工作,添加更多的人类语言,并测量模型可以学习什么。

英文摘要:

Some claim language models understand us. Others won't hear it. To clarify, I investigate three views of human language understanding: as-mapping, as-reliability and as-representation. I argue that while behavioral reliability is necessary for understanding, internal representations are sufficient; they climb the right hill. I review state-of-the-art language and multi-modal models: they are pragmatically challenged by under-specification of form. I question the Scaling Paradigm: limits on resources may prohibit scaled-up models from approaching understanding. Last, I describe how as-representation advances a science of understanding. We need work which probes model internals, adds more of human language, and measures what models can learn.

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。

↑