MIRAGE: 通过并行图检索增强推理链实现测试时扩展
MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains
AI总结：
MIRAGE通过并行图检索增强推理链实现测试时扩展，提升医疗问答任务的准确性和可追溯性。
摘要：
大型推理模型（LRMs）通过思维链提示在测试时扩展方面取得了显著进展。当前方法如search-o1将检索增强生成（RAG）整合到多步推理过程中，但依赖于单一的线性推理链，同时以扁平、无结构的方式整合非结构化文本信息。因此，这些方法会导致推理链中的误差累积，这在医疗问答（QA）任务中显著限制了其有效性，因为准确性和可追溯性都是关键要求。为了解决这些挑战，我们提出了MIRAGE（多链推理与检索增强图探索），一种新的测试时可扩展的推理框架，该框架在结构化医疗知识图上执行动态多链推理。具体而言，MIRAGE 1）将复杂查询分解为实体接地的子问题，2）执行并行推理链，3）通过邻居扩展和多跳遍历适配性检索证据，4）使用跨链验证整合答案以解决矛盾。在三个医疗QA基准（GenMedGPT-5k、CMCQA和ExplainCPE）上的实验表明，MIRAGE在自动和人工评估中均优于GPT-4o、树状思维链变体和其他检索增强基线。此外，MIRAGE通过生成显式的推理链来提高可解释性，每个事实主张都能追溯到知识图中的具体链，使其适用于复杂医疗推理场景。代码将供进一步研究使用。
英文摘要：
Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but rely on a single, linear reasoning chain while incorporating unstructured textual information in a flat, context-agnostic manner. As a result, these approaches can lead to error accumulation throughout the reasoning chain, which significantly limits its effectiveness in medical question-answering (QA) tasks where both accuracy and traceability are critical requirements. To address these challenges, we propose MIRAGE (Multi-chain Inference with Retrieval-Augmented Graph Exploration), a novel test-time scalable reasoning framework that performs dynamic multi-chain inference over structured medical knowledge graphs. Specifically, MIRAGE 1) decomposes complex queries into entity-grounded sub-questions, 2) executes parallel inference chains, 3) retrieves evidence adaptively via neighbor expansion and multi-hop traversal, and 4) integrates answers using cross-chain verification to resolve contradictions. Experiments on three medical QA benchmarks (GenMedGPT-5k, CMCQA, and ExplainCPE) show that MIRAGE consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations. Additionally, MIRAGE improves interpretability by generating explicit reasoning chains that trace each factual claim to concrete chains within the knowledge graph, making it well-suited for complex medical reasoning scenarios. The code will be available for further research.
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。
