# New Methods & Metrics for LFQA tasks

Source: [New Methods & Metrics for LFQA tasks](<https://www.sota2.com/research/paper/68fa6b7c1e209131cea2e7a7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:49:06.844Z

Authors: Suchismit Mahapatra, Vladimir Blagojevic, Pablo Bertorello, Prasanna Kumar

Published: 2021-12-26T18:38:05.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.13432>)

[PDF](<https://arxiv.org/pdf/2112.13432.pdf>)