用图谱导航降低医疗大模型幻觉，提升推理速度与可信度。
TTFT-Aware Graph Chain-of-Thought:Distance-Indexed Neural A* for Low-Hallucination Multi-Hop Medical Reasoning
- 基于图谱的精准路径搜索，实现毫秒级可行性判断。
- 混合算法使首次响应时间缩短，幻觉率下降37%以上。
- 适合临床部署，兼顾解释性与推理效率。
幻觉和不可解释的推理仍是临床大模型的重大缺陷。我们提出一个面向生产的GraphRAG系统，基于包含约700,000个节点的异构医学知识图谱，用于辅助生育咨询。核心思路是定向导航：通过有向剪枝地标标记（PLL）oracle提供精确距离，实现亚毫秒级可行性验证与简单路径枚举；轻量级AStarNet启发式算法严格在PLL走廊内运行，优先选择临床合理的扩展路径。对少量多样化路径（包含CUI/语义类型重叠、长度先验、来源先验）进行评分与打包，作为生成条件，形成紧凑提示，显著改善首次生成时间（TTFT）。在生育相关查询上，混合方案（PLL+AStarNet）在延迟与召回率之间达成更优权衡，相比纯文本RAG与单组件基线，显著降低TTFT并减少临床评估中的幻觉，同时保持解释清晰。该系统为可解释、低幻觉的多跳医疗推理提供了可落地的解决方案。
原文摘要 · Abstract (English)
Hallucinations and opaque reasoning remain unacceptable failure modes for clinical LLMs. We present a production-grade GraphRAG stack that constrains answers to verifiable graph chain-of-thought paths in a heterogeneous, ~700K-node medical knowledge graph powering a fertility assistant. The core idea is targeted navigation: a directed Pruned Landmark Labeling (PLL) oracle provides exact distances for sub-millisecond feasibility checks and simple-path enumeration, while a lightweight AStarNet heuristic operates strictly within the PLL corridor to prioritize clinically plausible expansions. We score and pack a small, diverse set of paths (CUI/semantic-type overlap, length prior, provenance priors) to condition generation, yielding compact prompts and improved Time to First Token (TTFT). On fertility-focused queries, the hybrid (PLL+AStarNet) establishes a better latency/recall Pareto frontier than text-only RAG and single-component baselines, lowers TTFT, and reduces clinician-audited hallucinations while preserving explanation clarity. The result is a practical recipe for explainable, low-hallucination multi-hop medical reasoning ready for real-world deployment.
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。