@inproceedings{helm-etal-2025-statistical,
title = "Statistical inference on black-box generative models in the data kernel perspective space",
author = "Helm, Hayden and
Acharyya, Aranyak and
Park, Youngser and
Duderstadt, Brandon and
Priebe, Carey",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.204/",
doi = "10.18653/v1/2025.findings-acl.204",
pages = "3955--3970",
ISBN = "979-8-89176-256-5",
abstract = "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 statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model{'}s pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="helm-etal-2025-statistical">
<titleInfo>
<title>Statistical inference on black-box generative models in the data kernel perspective space</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hayden</namePart>
<namePart type="family">Helm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aranyak</namePart>
<namePart type="family">Acharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngser</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brandon</namePart>
<namePart type="family">Duderstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carey</namePart>
<namePart type="family">Priebe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>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 statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model’s pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks.</abstract>
<identifier type="citekey">helm-etal-2025-statistical</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.204</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.204/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>3955</start>
<end>3970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical inference on black-box generative models in the data kernel perspective space
%A Helm, Hayden
%A Acharyya, Aranyak
%A Park, Youngser
%A Duderstadt, Brandon
%A Priebe, Carey
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F helm-etal-2025-statistical
%X 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 statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model’s pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks.
%R 10.18653/v1/2025.findings-acl.204
%U https://aclanthology.org/2025.findings-acl.204/
%U https://doi.org/10.18653/v1/2025.findings-acl.204
%P 3955-3970
Markdown (Informal)
[Statistical inference on black-box generative models in the data kernel perspective space](https://aclanthology.org/2025.findings-acl.204/) (Helm et al., Findings 2025)
ACL