语言化粒子后验：对自然语言假设的贝叶斯推断
Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses
浏览论文内容
中文总结 AI 辅助
研究针对语言化机器学习无不确定性度量等问题，提出语言化粒子后验方法，通过维护自然语言假设粒子并更新预测，在回归等基准测试中表现优于单个VML运行，能消除灾难性单运行失败，且后验可检查。
中文摘要 AI 辅助
语言化机器学习（VML）将模型参数化为大语言模型（LLM）评估为f(x;θ)的自然语言提示。该框架具有可解释性，但它致力于单个假设且没有不确定性度量，并且该假设在相同数据的优化运行中差异很大。我们提出了语言化粒子后验（VPP），将语言化学习视为贝叶斯推断问题：将自然语言假设群体作为粒子维护，使用Metropolis-Hastings（VPP-MH）或顺序蒙特卡罗（VPP-SMC）更新它们，并通过贝叶斯模型平均进行预测。两种算法都将LLM视为黑箱，无需访问对数its或梯度。在经典贝叶斯学习中，模型选择在后部之外；在VPP中，模型结构和参数共享一个单一语言空间，后部涵盖两者。我们在回归、分类和规则发现基准上评估VPP。它在每个基准上都比单个VML运行有所改进，并且在大多数情况下匹配或超过独立VML运行的最佳集成，同时消除了VML偶尔产生的灾难性单运行失败。由于每个粒子都是人类可读的假设，后验本身是读者可以检查的，能以明文形式看到数据支持哪些解释以及排除了哪些解释。
英文摘要
Verbalized Machine Learning (VML) parameterizes a model as a natural-language prompt that an LLM evaluates as f(x; theta). The framework is interpretable, but it commits to a single hypothesis with no measure of uncertainty, and that hypothesis varies substantially across optimization runs on the same data. We propose the Verbalized Particle Posterior (VPP), which treats verbalized learning as a Bayesian inference problem: maintain a population of natural-language hypotheses as particles, update them with Metropolis-Hastings (VPP-MH) or Sequential Monte Carlo (VPP-SMC), and predict by Bayesian model averaging. Both algorithms treat the LLM as a black box, requiring no access to logits or gradients. A distinctive consequence follows. In classical Bayesian learning, model selection sits outside the posterior; in VPP both model structure and parameters share a single language space, and the posterior ranges over both. We evaluate VPP on regression, classification, and rule-discovery benchmarks. It improves over a single VML run on every benchmark and matches or exceeds an oracle-best ensemble of independent VML runs on most, while eliminating the catastrophic single-run failures that VML occasionally produces. Because each particle is a human-readable hypothesis, the posterior is itself something a reader can inspect, seeing in plain text which explanations the data supported and which it ruled out.
发表机构
- Florida State University（佛罗里达州立大学）
机构由 AI 辅助整理，请以论文原文为准。
