Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials

arXiv:2402.19076v1 Announce Type: new
Abstract: In recent years, large language models have achieved state-of-the-art performance across various NLP tasks. However, investigations have shown that these models tend to rely on shortcut features, leading to inaccurate predictions and causing the models to be unreliable at generalization to out-of-distribution (OOD) samples. For instance, in the context of relation extraction (RE), we would expect a model to identify the same relation independently of the entities involved in it. For example, consider the sentence …

abstract art arxiv cs.cl distribution extraction features investigations language language models large language large language models nlp performance pointing out predictions shortcut state tasks type