Open-World Factually Consistent Question Generation
Himanshu Maheshwari, Sumit Shekhar, Apoorv Saxena, Niyati Chhaya · 2023
Question generation methods based on pretrained language models often suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph.Domain shift -where the test data is from a different domain than the training data -further exacerbates the problem of hallucination.This is a critical issue for any natural language application doing question generation.In this work, we propose an effective data processing technique based on de-lexicalization for consistent question generation across domains.Unlike existing approaches for remedying hallucination, the proposed approach does not filter training data and is generic across question-generation models.Experimental results across six benchmark datasets show that our model is robust to domain shift and produces entity-level factually consistent questions without significant impact on traditional metrics.