通道增强的多智能体系统与迭代咨询用于文档敏感性分类
A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification
查看机构详情
- Pakistan Institute of Engineering and Applied Sciences (PIEAS)（巴基斯坦工程与应用科学学院（PIEAS））
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出通道增强多智能体系统（IC-MAS），通过门控通道增强与迭代咨询解决长文档敏感性分类中截断丢失证据的问题，在降低计算成本的同时显著提升准确率与召回率。
中文摘要 AI 辅助
关键国家基础设施领域的组织在路由或存储前必须评估异构文档的敏感性。人工评估速度慢、不一致且不可扩展。在我们先前泄漏控制的基准基础上，BERT 建立了最佳单编码器基线（在 Strategic 16K 语料库上通过 5 折交叉验证达到 89.14% 的准确率和 89.33% 的 F1 分数）。然而，Transformer 基线存在结构性限制：固定输入长度截断会丢弃保留窗口之外的证据——而敏感电缆文档往往恰恰最长。我们提出了通道增强多智能体系统（CB-MAS）并将其实例化为 IC-MAS（迭代咨询多智能体系统），以在无长上下文计算成本的情况下解决此问题。一个通道评论智能体学习文档自适应的信任权重，用于控制两个首窗口编码器之间的门控通道增强，而配对的咨询智能体迭代交换信念状态，以协调长文档开头和结尾的证据。IC-MAS 通过在一个紧凑的表示空间中协调固定窗口，使计算量不随文档长度变化。消融研究表明，评论智能体控制的通道增强提供了大部分准确率提升，而咨询在不导致精确率崩溃的情况下恢复了召回率。评论智能体控制的门控通道增强与最大池化融合以及黑板自适应咨询实现了 90.72% 的准确率、91.23% 的 F1 分数、92.01% 的敏感召回率和 90.46% 的敏感精确率，同时比固定轮次基线平均节省约 54% 的计算量。相对于单编码器基线的提升具有统计显著性（McNemar 检验，p 小于 0.000001；配对 t 检验）。我们包含了 LIME/SHAP 可解释性、多智能体评估以及对局限性的诚实说明。
英文摘要
Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessment is slow, inconsistent, and unscalable. Extending our prior leakage-controlled benchmark, BERT established the top single-encoder baseline (89.14% accuracy, 89.33% F1-score under 5-fold cross-validation on the Strategic 16K corpus). However, transformer baselines suffer from a structural limitation: fixed input length truncation discards evidence beyond the retained window-precisely where sensitive cables tend to be longest. We present Channel-Boosted MAS (CB-MAS) and instantiate it as IC-MAS (Iterative Consultation Multi-Agent System) to solve this without long-context computational costs. A Channel Critic Agent learns document-adaptive trust weights governing Gated Channel Boosting between two first-window encoders, while paired Consultation Agents iteratively exchange belief states to reconcile evidence from the beginning and end of long documents. IC-MAS holds computation constant regardless of document length by reconciling fixed windows in a compact representation space. Ablation studies show critic-controlled Channel Boosting provides the bulk of accuracy gains, while consultation recovers recall without precision collapse. Critic-Controlled Gated Channel Boosting with Max-Pool fusion and Blackboard Adaptive Consultation achieves 90.72% accuracy, 91.23% F1-score, 92.01% sensitive recall, and 90.46% sensitive precision, using about 54% less average computation than a fixed-round baseline. Gains over the single-encoder baseline are statistically significant (McNemar's test, p less than 0.000001; paired t-test). We include LIME/SHAP explainability, multi-agent evaluation, and an honest accounting of limitations.
