用马尔的分析层次批判语言模型对人类语言理解的解释力

Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities

• 从马尔分析层次出发，审视语言模型的预测机制
• 指出仅靠机器估计概率无法完整解释人类语言处理
• 建议融合大模型与心理语言学模型的未来方向

基于马尔的分析层次框架，本文批判并拓展了关于语言模型（LMs）与语言处理的两个观点：其一，基于上下文预测下一个语言单元是语言处理的核心；其二，许多心理语言学进展离不开大型语言模型（LLMs）。文章进一步提出将大模型优势与心理语言学模型结合的未来研究方向，以更全面地理解人类语言处理机制。

原文摘要 · Abstract (English)

Under the lens of Marr's levels of analysis, we critique and extend two claims about language models (LMs) and language processing: first, that predicting upcoming linguistic information based on context is central to language processing, and second, that many advances in psycholinguistics would be impossible without large language models (LLMs). We further outline future directions that combine the strengths of LLMs with psycholinguistic models.

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。