Generative Long-form Question Answering: Relevance, Faithfulness and Succinctness

TL;DR

This thesis explores the under-studied task of Long Form Question Answering (LFQA), focusing on generating relevant, faithful, and succinct paragraph-length answers, and introduces new research directions for improving answer quality.

Contribution

It is among the first to investigate LFQA comprehensively, pioneering methods to enhance relevance, faithfulness, and succinctness of long-form answers.

Findings

Identified key challenges in LFQA such as relevance and faithfulness.

Proposed new approaches to improve answer quality in LFQA.

Laid groundwork for future research in long-form answer generation.

Abstract

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.