语义贝叶斯世界模型
Semantic Bayesian World Models
浏览论文内容
中文总结 AI 辅助
该研究针对知识图谱与概率推理系统的不匹配问题，提出语义贝叶斯世界模型，阐述其优势及所需构建的关键技术。
中文摘要 AI 辅助
知识图谱以明确断言描述现实，而当前使用它们的系统——基础模型与自主智能体——天然以概率进行推理。我们认为这种不匹配是语言模型与知识图谱的集成仍停留在数据馈送管道、而非统一推理架构的原因。我们提出语义贝叶斯世界模型（Semantic Bayesian World Models, SBWMs）：一种不将世界描述为事实数据库、而是描述为知识图谱上共享演化信念结构的网络，其中本体论公理约束先验，观测通过贝叶斯条件化更新信念，行动则干预世界。我们论证智能体从该模型中获得的收益：判断门口人物是快递员还是窃贼的家庭安保智能体、通过蕴含而非字符串频率聚合的精算估计、语言模型可靠失败的规划任务、以及对无任何文档陈述过的量的估计。随后我们明确该领域需构建的内容：RDF 1.2 上的信念标注、概率蕴含机制、语义校准层、以及从未交互过的智能体可交换并就校准信念产生分歧的协议。
英文摘要
Knowledge graphs describe reality in crisp assertions, while the systems now consuming them, foundation models and autonomous agents, reason natively in probabilities. We argue that this mismatch is why the integration of language models and knowledge graphs remains a data-feeding pipeline rather than a unified reasoning architecture. We envision Semantic Bayesian World Models (SBWMs): a Web that describes the world not as a database of facts but as a shared, evolving fabric of beliefs over knowledge graphs, where ontological axioms constrain priors, observations update beliefs by Bayesian conditioning, and actions intervene upon the world. We work through what an agent gains from such a model: a home-security agent deciding whether the figure at the gate is a courier or a burglar, an actuarial estimate aggregated by entailment rather than by string frequency, a planning task that language models reliably fail, and the estimation of quantities that no document has ever stated. We then set out what the community must build to make them possible: belief annotation over RDF~1.2, probabilistic entailment regimes, semantic calibration layers, and protocols by which agents that have never met can exchange, and disagree over, calibrated beliefs.
发表机构
- Liber AI Research（Liber AI研究院）
机构由 AI 辅助整理，请以论文原文为准。
