通过对比学习提升检索器逻辑推理能力，让大模型更懂复杂问题。
Logic-Oriented Retriever Enhancement via Contrastive Learning
- 用细粒度对比学习激活模型中隐藏的逻辑分析能力
- 在多个数据集上显著提升检索准确率和生成质量
- 无需额外标注或计算资源，适合现有检索系统直接部署
大型语言模型在知识密集型任务中表现不佳，因检索器常依赖表面相似性，难以处理涉及复杂逻辑关系的查询。模型表征中本就具备逻辑分析能力，但标准训练未能充分挖掘。LORE（Logic-Oriented Retriever Enhancement）引入细粒度对比学习，引导嵌入向与逻辑结构一致的证据对齐，而非仅依赖浅层相似性。该方法无需外部监督、额外资源或预检索分析，保持索引兼容性，持续提升检索效用与下游生成表现，同时保证效率。代码与数据集已公开于 https://github.com/mazehart/Lore-RAG。
原文摘要 · Abstract (English)
Large language models (LLMs) struggle in knowledge-intensive tasks, as retrievers often overfit to surface similarity and fail on queries involving complex logical relations. The capacity for logical analysis is inherent in model representations but remains underutilized in standard training. LORE (Logic ORiented Retriever Enhancement) introduces fine-grained contrastive learning to activate this latent capacity, guiding embeddings toward evidence aligned with logical structure rather than shallow similarity. LORE requires no external upervision, resources, or pre-retrieval analysis, remains index-compatible, and consistently improves retrieval utility and downstream generation while maintaining efficiency. The datasets and code are publicly available at https://github.com/mazehart/Lore-RAG.
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。