# A Critical Evaluation of Evaluations for Long-form Question Answering

Source: [A Critical Evaluation of Evaluations for Long-form Question Answering](<https://www.sota2.com/research/paper/68fa6f931e209131cea46611>)

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

Data updated: 2026-01-02T02:51:33.496Z

Authors: Fangyuan Xu, Yixiao Song, Mohit Iyyer, Eunsol Choi

Published: 2023-05-29T16:54:24.000Z

## Abstract

Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study of the evaluation of long-form answers, covering both human and automatic evaluation practices. We hire domain experts in seven areas to provide preference judgments over pairs of answers, along with free-form justifications for their choices. We present a careful analysis of experts' evaluation, which focuses on new aspects such as the comprehensiveness of the answer. Next, we examine automatic text generation metrics, finding that no existing metrics are predictive of human preference judgments. However, some metrics correlate with fine-grained aspects of answers (e.g., coherence). We encourage future work to move away from a single "overall score" of the answer and adopt a multi-faceted evaluation, targeting aspects such as factuality and completeness. We publicly release all of our annotations and code to spur future work into LFQA evaluation.

## 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/2305.18201>)

[PDF](<https://arxiv.org/pdf/2305.18201.pdf>)

[Implementation](<https://github.com/carriex/lfqa_eval>)