基于Transformer的问答模型与RAG增强设计的综合评估
A Comprehensive Evaluation of Transformer-Based Question Answering Models and RAG-Enhanced Design
AI总结：
本文综合评估了多跳问答中的检索策略，提出结合稠密嵌入、词法重叠与重排序的混合检索方法，并采用EfficientRAG进行查询优化，在HotpotQA上实现精确匹配相对提升50%、F1提升47%，验证了混合RAG作为零样本方案的实用价值。
摘要：
基于Transformer的模型推动了问答领域的发展，但多跳推理——即答案需要结合多个段落中的证据——仍然困难重重。本文对检索增强生成框架下的多跳问答检索策略进行了综合评估。我们比较了余弦相似度、最大边际相关性，以及一种将稠密嵌入与词法重叠和重排序相结合的混合方法。为了进一步改进检索，我们采用EfficientRAG流水线进行查询优化，引入令牌标注和迭代精炼，同时保持效率。在HotpotQA数据集上的实验表明，混合方法显著优于基线方法，与余弦相似度相比，精确匹配率相对提升50%，F1分数相对提升47%。错误分析显示，混合检索提高了实体召回率和证据互补性，但在处理干扰项和时间推理方面仍然存在局限。总体而言，结果表明混合检索增强生成为多跳问答提供了一种实用的零样本解决方案，在准确性、效率和可解释性之间取得了平衡。
英文摘要：
Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of retrieval strategies for multi-hop question answering within a retrieval-augmented generation framework. We compare cosine similarity, maximal marginal relevance, and a hybrid method that integrates dense embeddings with lexical overlap and re-ranking. To further improve retrieval, we adapt the EfficientRAG pipeline for query optimization, introducing token labeling and iterative refinement while maintaining efficiency. Experiments on the HotpotQA dataset show that the hybrid approach substantially outperforms baseline methods, achieving a relative improvement of 50 percent in exact match and 47 percent in F1 score compared to cosine similarity. Error analysis reveals that hybrid retrieval improves entity recall and evidence complementarity, while remaining limited in handling distractors and temporal reasoning. Overall, the results suggest that hybrid retrieval-augmented generation provides a practical zero-shot solution for multi-hop question answering, balancing accuracy, efficiency, and interpretability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
