Retrieval-Augmented Generation (RAG) models frequently produce answers grounded in parametric memory rather than the retrieved context, undermining the core promise of retrieval augmentation. A fundamental obstacle to fixing this unfaithfulness is the lack of training data that explicitly requires models to prefer context over internal knowledge. We introduce Faithfulness-QA, a large-scale dataset of 99,094 samples constructed through counterfactual entity substitution. Starting from two established extractive QA benchmarks--SQuAD and TriviaQA--we automatically identify answer-bearing named entities in each context, replace them with type-consistent alternatives drawn from a curated bank of 76,953 entities, and thereby manufacture controlled knowledge conflicts between context and parametric memory. Rigorous quality filtering ensures 100% pass rates across four automated checks on random 200-sample audits. We release the full dataset, the construction pipeline, and a typed entity bank covering eight named entity categories. Faithfulness-QA is designed as a training resource for attention-based faithfulness objectives and as an evaluation benchmark for measuring context-grounding behavior in RAG systems. Data and code are available at https://github.com/qzhangFDU/faithfulness-qa-dataset.

翻译：检索增强生成（RAG）模型经常产生基于参数化记忆而非检索上下文的答案，这削弱了检索增强的核心价值。解决这种不忠实的主要障碍在于缺乏明确要求模型优先考虑上下文而非内部知识的训练数据。我们提出忠实度问答（Faithfulness-QA），这是一个包含99,094个样本的大规模数据集，通过反事实实体替换构建而成。从两个成熟的抽取式问答基准（SQuAD和TriviaQA）出发，我们自动识别每个上下文中包含答案的命名实体，将其替换为来自包含76,953个实体的精选库中类型一致的替代实体，从而在上下文和参数化记忆之间制造可控的知识冲突。严格的质量过滤确保在随机抽取的200个样本审计中，四项自动检查均达到100%通过率。我们发布完整数据集、构建流程以及涵盖八类命名实体的类型化实体库。忠实度问答旨在作为基于注意力的忠实性目标的训练资源，以及衡量RAG系统中上下文接地行为的评估基准。数据和代码可在https://github.com/qzhangFDU/faithfulness-qa-dataset获取。