通过定位认知缺陷，让AI精准纠正人类错误背后的思维误区。
Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization
- 用知识图谱分析交互行为，定位用户错误根源
- 零样本泛化，可同时识别并纠正多个重叠误区
- 实测90%学生误区被成功修正，适合需要长期改进的协作场景
在人机协作中，AI助手常通过行为反馈（如警示或方向盘微调）纠正人类的次优行为。这类干预虽能缓解即时错误，但长期改进需解决导致重复出错的根本认知偏差。本文提出SENSEI框架，通过分析交互行为推断用户认知偏差，并提供针对性、最小且充分的改进建议。该方法不依赖动作或轨迹层面的干预，而是基于结构化知识表示，定位并修正错误行为的源头。在三个具有多样化认知偏差与对应行为的长时程任务中，SENSEI展现出零样本组合泛化能力，即使仅在单一偏差数据上训练，也能有效分离并纠正多个重叠的认知误区。用户研究进一步验证了该方法能准确识别真实人类认知偏差，并提供有效指导，显著提升长时程任务表现，成功修正了90%的学生认知误区。代码与项目页面见 https://misoshiruseijin.github.io/SENSEI/。
原文摘要 · Abstract (English)
AI assistants in human-AI collaboration often correct suboptimal human actions through behavioral feedback (e.g., alerts or steering-wheel nudges in assistive driving). Such interventions can mitigate immediate errors, but long-term improvement requires addressing the underlying misconceptions that cause repeated mistakes. We introduce SENSEI, a framework that infers user misconceptions from interaction behavior and provides targeted, minimal yet sufficient suggestions to correct them. Our approach departs from action- or trajectory-level interventions by operating over a structured knowledge representation to localize and correct the sources of erroneous behavior. Across three long-horizon tasks with diverse misconceptions and corresponding behaviors, SENSEI demonstrates zero-shot compositional generalization, disentangling multiple overlapping misconceptions despite training only on single-misconception cases. A user study further shows that our method identifies real human misconceptions and provides effective guidance that improves long-horizon task performance, successfully correcting $90\%$ of student misconceptions. Code and project page are available at https://misoshiruseijin.github.io/SENSEI/.
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。