Limits for learning with language models
Limits for learning with language models
复制标题
使用语言模型学习的局限性
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Soumya Paul
中科院分区：
文献类型：
--
作者：
Nicholas M. Asher;Swarnadeep Bhar;Akshay Chaturvedi;Julie Hunter;Soumya Paul
随着大型语言模型（LLM）的出现，NLP的趋势是培训大量数据以解决多样化的语言理解和发电任务。 LLM成功列表漫长而多样。然而，最近的几篇论文提供了经验证据，表明LLM无法捕获语言意义的重要方面。为了关注普遍量化，我们通过证明LLM无法学习某些基本的语义属性，包括语义上的必要性和一致性，因为它们在正式的语义中定义了，我们为这些经验发现提供了理论基础。更普遍地，我们表明，LLM无法学习超出第一层的Borel层次结构的概念，这对LMS（大小）的能力施加了严重的限制，以捕捉语言意义的许多方面。这意味着LLM将在没有正式保证需要的任务和深入语言理解的任务上运作。
With the advent of large language models (LLMs), the trend in NLP has been to train LLMs on vast amounts of data to solve diverse language understanding and generation tasks. The list of LLM successes is long and varied. Nevertheless, several recent papers provide empirical evidence that LLMs fail to capture important aspects of linguistic meaning. Focusing on universal quantification, we provide a theoretical foundation for these empirical findings by proving that LLMs cannot learn certain fundamental semantic properties including semantic entailment and consistency as they are defined in formal semantics. More generally, we show that LLMs are unable to learn concepts beyond the first level of the Borel Hierarchy, which imposes severe limits on the ability of LMs, both large and small, to capture many aspects of linguistic meaning. This means that LLMs will operate without formal guarantees on tasks that require entailments and deep linguistic understanding.
DOI：
--
发表时间：
2019
期刊：
Proceedings of the 22nd Amsterdam Colloquium
影响因子：
--
作者：
Graf, Thomas
通讯作者：
Graf, Thomas