This paper presents a method for estimating the hallucination rate for in-context learning (ICL) with generative AI. In ICL, a conditional generative model (CGM) is prompted with a dataset and a prediction question and asked to generate a response. One interpretation of ICL assumes that the CGM computes the posterior predictive of an unknown Bayesian model, which implicitly defines a joint distribution over observable datasets and latent mechanisms. This joint distribution factorizes into two components: the model prior over mechanisms and the model likelihood of datasets given a mechanism. With this perspective, we define a \textit{hallucination} as a generated response to the prediction question with low model likelihood given the mechanism. We develop a new method that takes an ICL problem and estimates the probability that a CGM will generate a hallucination. Our method only requires generating prediction questions and responses from the CGM and evaluating its response log probability. We empirically evaluate our method using large language models for synthetic regression and natural language ICL tasks.

Modern plant science increasingly relies on large, heterogeneous datasets, but challenges in experimental design, data preprocessing, and reproducibility hinder research throughput. Here we introduce Aleks, an AI-powered multi-agent system that integrates domain knowledge, data analysis, and machine learning within a structured framework to autonomously conduct data-driven scientific discovery. Once provided with a research question and dataset, Aleks iteratively formulated problems, explored alternative modeling strategies, and refined solutions across multiple cycles without human intervention. In a case study on grapevine red blotch disease, Aleks progressively identified biologically meaningful features and converged on interpretable models with robust performance. Ablation studies underscored the importance of domain knowledge and memory for coherent outcomes. This exploratory work highlights the promise of agentic AI as an autonomous collaborator for accelerating scientific discovery in plant sciences.

This paper presents a method for estimating the hallucination rate for in-context learning (ICL) with generative AI. In ICL, a conditional generative model (CGM) is prompted with a dataset and a prediction question and asked to generate a response. One interpretation of ICL assumes that the CGM computes the posterior predictive of an unknown Bayesian model, which implicitly defines a joint distribution over observable datasets and latent mechanisms. This joint distribution factorizes into two components: the model prior over mechanisms and the model likelihood of datasets given a mechanism. With this perspective, we define a \textit{hallucination} as a generated response to the prediction question with low model likelihood given the mechanism.