Question Answering (QA) in NLP is the task of finding answers to a query within a relevant context retrieved by a retrieval system. Yet, the mix of relevant and irrelevant information in these contexts can hinder performance enhancements in QA tasks. To address this, we introduce a context filtering approach that removes non-essential details, summarizing crucial content through Reward Modeling. This method emphasizes keeping vital data while omitting the extraneous during summarization model training. We offer a framework for developing efficient QA models by discerning useful information from dataset pairs, bypassing the need for costly human evaluation. Furthermore, we show that our approach can significantly outperform the baseline, as evidenced by a 6.8-fold increase in the EM Per Token (EPT) metric, which we propose as a measure of token efficiency, indicating a notable token-efficiency boost for low-resource settings.

翻译：自然语言处理中的问答任务旨在从检索系统获取的相关上下文中查找查询的答案。然而，这些上下文中相关与无关信息的混杂可能阻碍问答任务的性能提升。为此，我们提出一种上下文过滤方法，通过奖励建模去除非必要细节并总结关键内容。该方法在摘要模型训练过程中强调保留关键数据同时剔除冗余信息。我们通过从数据集对中识别有用信息，提供了一种开发高效问答模型的框架，从而避免昂贵的人工评估需求。此外，我们证明该方法能显著超越基线模型，具体表现为EM Per Token指标提升6.8倍——该指标是我们提出的用于衡量标记效率的度量标准，表明在低资源环境下实现了显著的标记效率提升。