零样本检索增强问答框架，提升常识推理准确率与可解释性
ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering
- 不需训练，通过检索相关问答对并推理生成新知识
- 在8个基准上平均提效4.5点，最高超越强模型表现
- 适合追求高可解释性、无额外训练成本的场景
当前大语言模型在常识推理任务中展现出强大能力，但其决策过程仍不透明。现有方法虽引入知识检索、推理与自我反思机制以提升性能与可解释性，但通常需额外训练、手工模板或人工编写解释。为此，我们提出ZEBRA——一种零样本问答框架，结合检索、案例推理与自我反思，无需微调大模型。给定输入问题，ZEBRA从知识库中检索相关问答对，基于其关系推理生成新知识，并用于回答原问题，从而提升性能与输出可解释性。我们在8个主流常识推理基准上评估该方法，结果表明ZEBRA持续优于强基线模型及以往知识融合方法，平均准确率提升达4.5个百分点。
原文摘要 · Abstract (English)
Current Large Language Models (LLMs) have shown strong reasoning capabilities in commonsense question answering benchmarks, but the process underlying their success remains largely opaque. As a consequence, recent approaches have equipped LLMs with mechanisms for knowledge retrieval, reasoning and introspection, not only to improve their capabilities but also to enhance the interpretability of their outputs. However, these methods require additional training, hand-crafted templates or human-written explanations. To address these issues, we introduce ZEBRA, a zero-shot question answering framework that combines retrieval, case-based reasoning and introspection and dispenses with the need for additional training of the LLM. Given an input question, ZEBRA retrieves relevant question-knowledge pairs from a knowledge base and generates new knowledge by reasoning over the relationships in these pairs. This generated knowledge is then used to answer the input question, improving the model's performance and interpretability. We evaluate our approach across 8 well-established commonsense reasoning benchmarks, demonstrating that ZEBRA consistently outperforms strong LLMs and previous knowledge integration approaches, achieving an average accuracy improvement of up to 4.5 points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。