Consistent estimation of generative model representations in the data kernel perspective space
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:AZA3F3OLrecord.jsonopen to challenge →
read the original abstract
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 information when presented the same query. As the landscape of generative models evolves, it is important to develop techniques to study and analyze differences in model behaviour. In this paper we present novel theoretical results for embedding-based representations of generative models in the context of a set of queries. In particular, we establish sufficient conditions for the consistent estimation of the model embeddings in situations where the query set and the number of models grow.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
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.
-
Black-box model classification under the discriminative factorization
Discriminative factorization distinguishes high-quality query sets for black-box model classification, with chance-level error decaying exponentially in query budget and parameters predicting empirical decay rates on ...
-
Query-efficient model evaluation using cached responses
DKPS-based methods leverage cached model responses to achieve equivalent benchmark prediction accuracy with substantially fewer queries than standard evaluation.
-
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.
-
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
Behavioral geometry of model populations enables high-accuracy jailbreak susceptibility prediction and defense transfer with 98% fewer evaluations.
-
Control Charts for Multi-agent Systems
Adaptive control charts can monitor learning multi-agent systems but are vulnerable to gradual adversarial defection, revealing a fundamental tradeoff between allowing agents to learn and maintaining security against ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.