Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis

Autor:	Ban, Pangbo, Jiang, Yifan, Liu, Tianran, Steinert-Threlkeld, Shane
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence 68T50 I.2.7
Druh dokumentu:	Working Paper
Popis:	To what extent do pre-trained language models grasp semantic knowledge regarding the phenomenon of distributivity? In this paper, we introduce DistNLI, a new diagnostic dataset for natural language inference that targets the semantic difference arising from distributivity, and employ the causal mediation analysis framework to quantify the model behavior and explore the underlying mechanism in this semantically-related task. We find that the extent of models' understanding is associated with model size and vocabulary size. We also provide insights into how models encode such high-level semantic knowledge. Comment: Accepted at BlackboxNLP 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.04761 Zobrazit plný text záznamu View this record from Arxiv