8 papers
Concentration bounds on response-based vector embeddings of black-box generative models
Aranyak Acharyya, Joshua Agterberg, Youngser Park +1
Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries. Response-based vector embeddings of gener…
Optimal control of the future via prospective learning with control
Yuxin Bai, Aranyak Acharyya, Ashwin De Silva +3
Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (RL). RL is mathematically distinct fro…
Recovering manifold structure in LLM responses through a joint Euclidean mirror
Maximilian Baum, Aranyak Acharyya, Tianyi Chen +5
Understanding the behavior of black-box large language models and determining effective means of comparing their performance is a key task in modern machine learning. We consider h…
Testing for LLM response differences: the case of a composite null consisting of semantically irrelevant query perturbations
Aranyak Acharyya, Carey E. Priebe, Hayden S. Helm
Given an input query, generative models such as large language models produce a random response drawn from a response distribution. Given two input queries, it is natural to ask if…
Statistical inference on black-box generative models in the data kernel perspective space
Hayden Helm, Aranyak Acharyya, Brandon Duderstadt +2
Generative models are capable of producing human-expert level content across a variety of topics and domains. As the impact of generative models grows, it is necessary to develop s…
Consistent estimation of generative model representations in the data kernel perspective space
Aranyak Acharyya, Michael W. Trosset, Carey E. Priebe +1
Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different inf…