LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models
This provides a new benchmark for researchers working on compositional generalization and inference in AI, though it is incremental as it builds on existing evaluation efforts.
The authors tackled the problem of evaluating logical inference abilities in seq2seq models by introducing LogicInference, a new dataset covering propositional and first-order logic in both logical notation and natural language, and reported initial baseline results from various machine learning models.
Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist to evaluate compositional generalization, when it comes to evaluating inference abilities, options are more limited. This paper presents LogicInference, a new dataset to evaluate the ability of models to perform logical inference. The dataset focuses on inference using propositional logic and a small subset of first-order logic, represented both in semi-formal logical notation, as well as in natural language. We also report initial results using a collection of machine learning models to establish an initial baseline in this dataset.