用可审计的修复框架，让大模型生成的科学推理图更准确可靠。
PEARL: Auditable Repair for Scientific Reasoning Graph Extraction
- 基于皮尔士符号学框架，将噪声推理图转为结构化表达
- 在五个数据集上将严格通过率从0提升至85.7%（300/350）
- 适合需要可追溯推理链的研究代理与AI科学家使用
科学推理图提取（SRGE）旨在恢复观测、证据、中间论断与论文结论之间的显式关联。大语言模型虽能生成类图推理，但常出现语法错误、边标签漂移、根节点方向错误及弱源锚定等问题。本文提出无需训练的PEARL（Peircean Extraction via Abstraction and Repair Layer）框架，将噪声输出转化为可审计的语义有效推理图，并通过匹配证据的判别反馈修复错误边类型、局部推理步骤与终端根节点，同时保留审计轨迹。在来自ARCHE基准的五个70篇论文数据集上，严格通过率从基线的0/350提升至300/350，平均推理准确性（REA）由0.339升至0.906。该方法为需可检查推理路径的研究代理与人工智能科学家提供可靠性保障。代码与审计资源见https://github.com/BohanSu/auditable-repair-reasoning-graphs/tree/300-350_workshop。
原文摘要 · Abstract (English)
Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions. LLMs can produce graph-like scientific explanations, but their outputs often mix malformed syntax, drifting edge labels, incorrectly oriented roots, and weak source anchors. We propose PEARL (Peircean Extraction via Abstraction and Repair Layer), a training-free framework that turns noisy LLM graph responses into auditable reasoning graphs and repairs them toward strict semantic validity. PEARL first materializes explicit graph content under a closed Peircean schema, then uses matched evidence-grounded judge feedback to repair rejected edge types, local inference steps, and terminal roots while preserving an audit trail. On five 70-paper model archives from ARCHE, a benchmark for latent reasoning-chain extraction, PEARL raises strict gate passes from 0/350 for the LLM baseline to 300/350, with average REA improving from 0.339 to 0.906. The graphs provide a reliability layer for research-agent and AI scientist workflows that need inspectable reasoning traces rather than unconstrained graph regeneration. Code and audit artifacts are available at https://github.com/BohanSu/auditable-repair-reasoning-graphs/tree/300-350_workshop .
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。