Natural Language Explanations (NLE) aim at supplementing the prediction of a model with human-friendly natural text. Existing NLE approaches involve training separate models for each downstream task. In this work, we propose Uni-NLX, a unified framework that consolidates all NLE tasks into a single and compact multi-task model using a unified training objective of text generation. Additionally, we introduce two new NLE datasets: 1) ImageNetX, a dataset of 144K samples for explaining ImageNet categories, and 2) VQA-ParaX, a dataset of 123K samples for explaining the task of Visual Question Answering (VQA). Both datasets are derived leveraging large language models (LLMs). By training on the 1M combined NLE samples, our single unified framework is capable of simultaneously performing seven NLE tasks including VQA, visual recognition and visual reasoning tasks with 7X fewer parameters, demonstrating comparable performance to the independent task-specific models in previous approaches, and in certain tasks even outperforming them. Code is at https://github.com/fawazsammani/uni-nlx

翻译：自然语言解释（NLE）旨在通过人类可理解的自然文本补充模型的预测结果。现有NLE方法需针对每个下游任务训练独立模型。本文提出Uni-NLX，一个统一框架，通过文本生成的统一训练目标，将所有NLE任务整合至单个紧凑的多任务模型中。此外，我们引入了两个新NLE数据集：1) ImageNetX——144K样本数据集用于解释ImageNet类别，2) VQA-ParaX——123K样本数据集用于解释视觉问答（VQA）任务。这两个数据集均利用大型语言模型（LLMs）生成。通过在100万组合NLE样本上训练，我们的单一统一框架能够同时执行七项NLE任务，包括VQA、视觉识别及视觉推理任务，参数量减少7倍，性能与先前方法中独立的任务特定模型相当，并在某些任务上实现超越。代码见https://github.com/fawazsammani/uni-nlx