A joint Euclidean mirror embeds LLM response distributions to recover manifold structure with respect to tuning parameters, enabling consistent inference of those parameters from samples.
Concentration bounds on response-based vector embeddings of black-box generative models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
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 generative models facilitate statistical analysis and inference on a given collection of black-box generative models. The Data Kernel Perspective Space embedding is one particular method of obtaining response-based vector embeddings for a given set of generative models, already discussed in the literature. In this paper, under appropriate regularity conditions, we establish high probability concentration bounds on the sample vector embeddings for a given set of generative models, obtained through the method of Data Kernel Perspective Space embedding. Our results tell us the required number of sample responses needed in order to approximate the population-level vector embeddings with a desired level of accuracy. The algebraic tools used to establish our results can be used further for establishing concentration bounds on Classical Multidimensional Scaling embeddings in general, when the dissimilarities are observed with noise.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DKPS-based methods predict new model benchmark scores using cached responses, matching baseline mean absolute error with substantially fewer queries and an offline query selection approach.
citing papers explorer
-
Recovering manifold structure in LLM responses through a joint Euclidean mirror
A joint Euclidean mirror embeds LLM response distributions to recover manifold structure with respect to tuning parameters, enabling consistent inference of those parameters from samples.
-
Query-efficient model evaluation using cached responses
DKPS-based methods predict new model benchmark scores using cached responses, matching baseline mean absolute error with substantially fewer queries and an offline query selection approach.