paper-with-me

홈 › Papers

Automated Statistical Model Discovery with Language Models

2024-02-27 · Michael Y. Li, Emily B. Fox, Noah D. Goodman

Statistical model discovery is a challenging search over a vast space of models subject to domain-specific constraints. Efficiently searching over this space requires expertise in modeling and the problem domain. Motivated by the domain knowledge and programming capabilities of large language models (LMs), we introduce a method for language model driven automated statistical model discovery. We cast our automated procedure within the principled framework of Box's Loop: the LM iterates between proposing statistical models represented as probabilistic programs, acting as a modeler, and critiquing those models, acting as a domain expert. By leveraging LMs, we do not have to define a domain-specific language of models or design a handcrafted search procedure, which are key restrictions of previous systems. We evaluate our method in three settings in probabilistic modeling: searching within a restricted space of models, searching over an open-ended space, and improving expert models under natural language constraints (e.g., this model should be interpretable to an ecologist). Our method identifies models on par with human expert designed models and extends classic models in interpretable ways. Our results highlight the promise of LM-driven model discovery.

📄 PDF Abstract BibTeX arXiv:2402.17879

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModellingmodelModel Discovery

Similar Papers 제목 키워드 기반

Automated Interpretability and Feature Discovery in Language Models with Agents

2026-05-02 · Arnau Marin-Llobet, Javier Ferrando arxiv

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation r…

AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing

2025-10-24 · Samuel Bright-Thonney, Christina Reissel, Gaia Grosso, Nathaniel Woodward 외 arxiv

Novelty detection in large scientific datasets faces two key challenges: the noisy and high-dimensional nature of experimental data, and the necessity of making statistically robust statements about any observed outliers…

Dimensionality ReductionData AugmentationAnomaly Detection

From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models

2025-06-02 · Yihong Tang, Ao Qu, Xujing Yu, Weipeng Deng 외

Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate actionable insights that guide the planning…

Large Language ModelMultimodal Large Language Modelscientific discovery

Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

2026-04-03 · Yao Zhao, Zhiyue Zhang, Yanxun Xu arxiv

Clinical evidence synthesis requires identifying relevant trials from large registries and aggregating results that account for population differences. While recent LLM-based approaches have automated components of syste…

InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI

2026-04-05 · Can Wang, Hongyu Zhao, Yiqun Chen arxiv

Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artifici…

Causal Inference