New Methods & Metrics for LFQA tasks
This work addresses critical bottlenecks for researchers and practitioners in LFQA, though it appears incremental as it builds on existing methods to solve known problems.
The paper tackled fundamental issues in long-form question answering (LFQA), including dataset overlap, lack of automatic metrics, and ungrounded answers, by introducing natural language inference/generation methods and metrics that significantly alleviate these bottlenecks.
Long-form question answering (LFQA) tasks require retrieving the documents pertinent to a query, using them to form a paragraph-length answer. Despite considerable progress in LFQA modeling, fundamental issues impede its progress: i) train/validation/test dataset overlap, ii) absence of automatic metrics and iii) generated answers not being "grounded" in retrieved documents. This work addresses every one these critical bottlenecks, contributing natural language inference/generation (NLI/NLG) methods and metrics that make significant strides to their alleviation.