Dissociable Neural Mechanisms for Human Inference Processing Predicted by Static and Contextual Language Models
Dissociable Neural Mechanisms for Human Inference Processing Predicted by Static and Contextual Language Models
复制标题
DOI：
10.1162/nol_a_00090
复制
发表时间：
2024-04-01
影响因子：
3.2
通讯作者：
Dominey，Peter Ford
中科院分区：
文献类型：
--
作者：
Uchida，Takahisa;Lair，Nicolas;Dominey，Peter Ford
语言模型（LM）继续揭示人类语言表现和潜在神经生理学的重要关系。最近的研究表明，如何从LM的词嵌入可以用来生成综合的话语表征，以执行推理的事件。目前的研究调查如何这样的事件知识可能会在不同类别的LM不同的方式编码，以及如何映射到不同形式的人类推理处理。要做到这一点，我们调查推理的事件使用两个有据可查的人类实验协议，从和，相比，两个协议更简单的语义处理。有趣的是，这揭示了本地语义与事件推理依赖于LM之间的关系的解离。在一系列的实验中，我们观察到，对于静态LM（word 2 vec/GloVe），有一个明显的分离的语义和推理的两个推理任务之间的关系。与此相反，对于上下文LM（BERT/RoBERTA），我们观察到语义和推理处理的推理任务之间的相关性。实验结果表明，MetJerusalem和McKoon测量的推理依赖于可分离的过程。虽然静态模型能够执行MetJerusalem推理，但只有上下文模型才能成功地进行McKoon推理。有趣的是，这些可分离的过程可能与心理学文献中的自动推理过程和策略推理过程有关。这使我们能够预测在人类推理处理这些任务时应该发现的可分离的神经生理标记。
Language models (LMs) continue to reveal non-trivial relations to human language performance and the underlying neurophysiology. Recent research has characterized how word embeddings from an LM can be used to generate integrated discourse representations in order to perform inference on events. The current research investigates how such event knowledge may be coded in distinct manners in different classes of LMs and how this maps onto different forms of human inference processing. To do so, we investigate inference on events using two well-documented human experimental protocols from and , compared with two protocols for simpler semantic processing. Interestingly, this reveals a dissociation in the relation between local semantics versus event-inference depending on the LM. In a series of experiments, we observed that for the static LMs (word2vec/GloVe), there was a clear dissociation in the relation between semantics and inference for the two inference tasks. In contrast, for the contextual LMs (BERT/RoBERTa), we observed a correlation between semantic and inference processing for both inference tasks. The experimental results suggest that inference as measured by Metusalem and McKoon rely on dissociable processes. While the static models are able to perform Metusalem inference, only the contextual models succeed in McKoon inference. Interestingly, these dissociable processes may be linked to well-characterized automatic versus strategic inference processes in the psychological literature. This allows us to make predictions about dissociable neurophysiological markers that should be found during human inference processing with these tasks.