Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models

arXiv:2404.02622v1 Announce Type: new
Abstract: Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability and model evaluation perspective, that it is valuable to investigate specific patterns of reasoning with enough structure and regularity to identify and quantify systematic reasoning failures in widely-used models. In this vein, we pick a portion of the NLI …

abstract analysis arxiv causal cs.cl effects evaluation features form however interpretability language language model logic natural natural language perspective predictions reasoning semantic transformer type