用检索匹配取代生成，防止大模型幻觉，提升合规服务可靠性。
RAL2M: Retrieval Augmented Learning-To-Match Against Hallucination in Compliance-Guaranteed Service Systems
- 将大模型改为检索系统中的问答匹配裁判，避免生成幻觉。
- 通过自适应潜在集成策略，实现多模型共识决策，显著提升准确率。
- 适合构建高可信度的合规服务系统，如金融、医疗问答场景。
在大模型驱动的服务系统中，幻觉问题严重威胁响应合规性，亟需显式知识支撑。本文提出检索增强型学习匹配框架RAL2M，将大模型定位为基于检索系统的问答匹配判官，替代纯生成方法，提供更可靠的解决方案。为缓解判断幻觉，我们设计了查询自适应的潜在集成策略，显式建模不同大模型的能力差异及其相互依赖关系，生成校准后的共识决策。大规模基准测试表明，该方法有效利用了“群体智慧”，显著优于多个强基线模型。最后，本文讨论了未来利用潜在表示的优化实践与研究方向。
原文摘要 · Abstract (English)
Hallucination is a major concern in LLM-driven service systems, necessitating explicit knowledge grounding for compliance-guaranteed responses. In this paper, we introduce Retrieval-Augmented Learning-to-Match (RAL2M), a novel framework that eliminates generation hallucination by repositioning LLMs as query-response matching judges within a retrieval-based system, providing a robust alternative to purely generative approaches. To further mitigate judgment hallucination, we propose a query-adaptive latent ensemble strategy that explicitly models heterogeneous model competence and interdependencies among LLMs, deriving a calibrated consensus decision. Extensive experiments on large-scale benchmarks demonstrate that the proposed method effectively leverages the "wisdom of the crowd" and significantly outperforms strong baselines. Finally, we discuss best practices and promising directions for further exploiting latent representations in future work.
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。