Read before Generate! Faithful Long Form Question Answering with Machine Reading
This addresses the challenge of faithfulness in long-form question answering for applications requiring reliable information, though it is incremental as it builds on existing generation models.
The paper tackles the problem of generating faithful, less hallucinated answers in long-form question answering by proposing a framework that jointly models answer generation and machine reading, achieving state-of-the-art results on ELI5 and MS MARCO datasets.
Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. While current work on LFQA using large pre-trained model for generation are effective at producing fluent and somewhat relevant content, one primary challenge lies in how to generate a faithful answer that has less hallucinated content. We propose a new end-to-end framework that jointly models answer generation and machine reading. The key idea is to augment the generation model with fine-grained, answer-related salient information which can be viewed as an emphasis on faithful facts. State-of-the-art results on two LFQA datasets, ELI5 and MS MARCO, demonstrate the effectiveness of our method, in comparison with strong baselines on automatic and human evaluation metrics. A detailed analysis further proves the competency of our methods in generating fluent, relevant, and more faithful answers.