arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.04416cs.AI
收藏

复杂人工智能系统中的传递专家误差与路由问题

Transitive Expert Error and Routing Problems in Complex AI Systems

Forest Mars

AI总结:

复杂AI系统中,传递专家误差导致领域边界处因果错误输出,通过多专家激活、边界校准和覆盖检测等干预措施加以解决。

摘要:

领域专业知识在边界内增强判断能力,但会在边界处产生系统性漏洞。我们将其称为传递专家误差(TEE),与杜宁-克鲁格效应不同,需要校准的专业知识作为前提。使可靠领域内判断的机制在结构相似性掩盖因果差异时会变成劣势。两个核心机制起作用:结构相似性偏差导致专家过度重视表面特征(共享词汇、模式、形式结构)而忽略因果架构差异;权威持续性通过社会强化和元认知失败维持信心,专家在跨能力边界时体验不到主观不确定性,因为模式识别在看似熟悉的输入上运作顺畅。这些机制在三个条件下加剧:共享词汇掩盖不同过程、社会压力要求立即判断、反馈延迟。这些发现扩展到AI路由架构(MoE系统、多模型协调、工具使用代理、RAG系统),表现出路由导致的失败(选择错误专家)和覆盖导致的失败(没有合适专家)。两者产生幻觉表型:自信、连贯、结构合理但因果错误的输出在领域边界。在人类系统中,这些机制是认知黑箱;AI架构使其显式且可解决。我们提出干预措施:多专家激活与分歧检测(路由器层面)、边界意识校准(专家层面)、覆盖缺口检测(训练层面)。TEE有可检测的特征(路由模式、自信-准确性脱节、领域不适当的内内容),可进行监控和缓解。在人类认知中难以解决的问题通过架构设计变得可解决。

英文摘要:

Domain expertise enhances judgment within boundaries but creates systematic vulnerabilities specifically at borders. We term this Transitive Expert Error (TEE), distinct from Dunning-Kruger effects, requiring calibrated expertise as precondition. Mechanisms enabling reliable within-domain judgment become liabilities when structural similarity masks causal divergence. Two core mechanisms operate: structural similarity bias causes experts to overweight surface features (shared vocabulary, patterns, formal structure) while missing causal architecture differences; authority persistence maintains confidence across competence boundaries through social reinforcement and metacognitive failures (experts experience no subjective uncertainty as pattern recognition operates smoothly on familiar-seeming inputs.) These mechanism intensify under three conditions: shared vocabulary masking divergent processes, social pressure for immediate judgment, and delayed feedback. These findings extend to AI routing architectures (MoE systems, multi-model orchestration, tool-using agents, RAG systems) exhibiting routing-induced failures (wrong specialist selected) and coverage-induced failures (no appropriate specialist exists). Both produce a hallucination phenotype: confident, coherent, structurally plausible but causally incorrect outputs at domain boundaries. In human systems where mechanisms are cognitive black boxes; AI architectures make them explicit and addressable. We propose interventions: multi-expert activation with disagreement detection (router level), boundary-aware calibration (specialist level), and coverage gap detection (training level). TEE has detectable signatures (routing patterns, confidence-accuracy dissociations, domain-inappropriate content) enabling monitoring and mitigation. What remains intractable in human cognition becomes addressable through architectural design.

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。

↑