Generative Long-form Question Answering: Relevance, Faithfulness and Succinctness
This work addresses the problem of generating in-depth, accurate, and concise answers for users in scenarios where existing QA models only provide short-span answers, representing a foundational but incremental step in LFQA.
The thesis tackled the challenge of generating high-quality long-form answers in Long Form Question Answering (LFQA) by focusing on improving relevance, faithfulness, and succinctness, pioneering research in this under-explored area.
In this thesis, we investigated the relevance, faithfulness, and succinctness aspects of Long Form Question Answering (LFQA). LFQA aims to generate an in-depth, paragraph-length answer for a given question, to help bridge the gap between real scenarios and the existing open-domain QA models which can only extract short-span answers. LFQA is quite challenging and under-explored. Few works have been done to build an effective LFQA system. It is even more challenging to generate a good-quality long-form answer relevant to the query and faithful to facts, since a considerable amount of redundant, complementary, or contradictory information will be contained in the retrieved documents. Moreover, no prior work has been investigated to generate succinct answers. We are among the first to research the LFQA task. We pioneered the research direction to improve the answer quality in terms of 1) query-relevance, 2) answer faithfulness, and 3) answer succinctness.