IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
This addresses the problem of improving logical reasoning in MRC systems, which is incremental as it builds on existing pre-trained models with a novel pre-training task.
The paper tackles the challenge of logical reasoning in machine reading comprehension by proposing IDOL, an indicator-oriented logic pre-training method that achieves state-of-the-art performance on benchmarks like ReClor and LogiQA, with generalization to other MRC tasks and competitive results on GLUE.
In the field of machine reading comprehension (MRC), existing systems have surpassed the average performance of human beings in many tasks like SQuAD. However, there is still a long way to go when it comes to logical reasoning. Although some methods for it have been put forward, they either are designed in a quite complicated way or rely too much on external structures. In this paper, we proposed IDOL (InDicator-Oriented Logic Pre-training), an easy-to-understand but highly effective further pre-training task which logically strengthens the pre-trained models with the help of 6 types of logical indicators and a logically rich dataset LGP (LoGic Pre-training). IDOL achieves state-of-the-art performance on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC, and is proven to be capable of generalizing to different pre-trained models and other types of MRC benchmarks like RACE and SQuAD 2.0 while keeping competitive general language understanding ability through testing on tasks in GLUE. Besides, at the beginning of the era of large language models, we take several of them like ChatGPT into comparison and find that IDOL still shows its advantage.