发表机构
Anthropic(Anthropic)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
研究提出结合大语言模型与神经仿真推理的框架,用于联合模型选择与参数估计。给定自然语言描述,大语言模型提出候选程序,经反馈驱动变异和神经密度估计评估,能在一组模型上推理,在多基准测试中可从提示识别合理模型族。
AI 中文摘要
神经仿真推理可对复杂模型进行参数估计,但通常需用户指定编码固定模型结构的模拟器。我们提出了一个联合模型选择与参数估计框架,将用于程序合成的大语言模型与基于神经仿真的推理相结合。给定对所研究系统和数据的自然语言描述,大语言模型提出候选模拟器程序,通过反馈驱动的变异进行迭代优化,并使用神经密度估计进行评估。该方法能对一组模型进行基于仿真的推理,而非仅对固定模型内的参数。在跨越确定性动力学、随机流行病模型以及引力透镜图像暗物质子结构推理的基准测试中,该方法能从开放式提示中识别出合理的模型族,其准确性反映了数据的信息内容和候选模型的可识别性。
英文摘要
Neural simulation-based inference enables parameter estimation for complex models, but typically requires the user to specify a simulator encoding a fixed model structure. We present a framework for joint model selection and parameter estimation that combines large language models for program synthesis with neural simulation-based inference. Given a natural language description of the system and data under investigation, an LLM proposes candidate simulator programs which are iteratively refined via feedback-driven mutation and evaluated using neural density estimation. The approach enables simulation-based inference over a pool of models, not just parameters within a fixed model. On benchmarks spanning deterministic dynamics, stochastic epidemic models, and dark matter substructure inference from gravitational-lensing images, the method identifies plausible model families from open-ended prompts, with accuracy that reflects the information content of the data and identifiability of candidate models.
Comments15+7 pages, 4+2 figures