SETI: Systematicity Evaluation of Textual Inference
This addresses the problem of assessing systematic reasoning in language models for NLP researchers, though it is incremental as it builds on existing evaluation frameworks.
The authors introduced SETI, a benchmark to evaluate pre-trained language models' systematicity in textual inference, finding that models perform well when they have compositional knowledge but suffer significant performance drops (40-100% points) without it, and can improve quickly with minimal exposure to such knowledge.
We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference. Specifically, SETI offers three different NLI tasks and corresponding datasets to evaluate various types of systematicity in reasoning processes. In order to solve these tasks, models are required to perform compositional inference based on known primitive constituents. We conduct experiments of SETI on six widely used PLMs. Results show that various PLMs are able to solve unseen compositional inferences when having encountered the knowledge of how to combine primitives, with good performance. However, they are considerably limited when this knowledge is unknown to the model (40-100% points decrease). Furthermore, we find that PLMs can improve drastically once exposed to crucial compositional knowledge in minimalistic shots. These findings position SETI as the first benchmark for measuring the future progress of PLMs in achieving systematicity generalization in the textual inference.