@inproceedings{jiang-etal-2026-flare,
title = "{FLARE}: Task-Agnostic Embedding Model Evaluation via Normalizing Flows",
author = "Jiang, Jingzhou and
Tang, Yixuan and
Yang, Yi and
Tam, Kar Yan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1957/",
doi = "10.18653/v1/2026.findings-acl.1957",
pages = "39271--39294",
ISBN = "979-8-89176-395-1",
abstract = "Despite the widespread adoption of text embedding models, selecting the optimal model for a specific target corpus remains challenging due to the lack of task-specific labels. While task-agnostic evaluation offers a promising solution by relying on unlabeled data, existing approaches based on kernel estimators or Gaussian mixtures fail to model high-dimensional distributions effectively, resulting in unstable rankings. To address this limitation, we propose FLARE (Flow-based Label-free Assessment of Representation Embeddings), which employs normalizing flows to estimate information sufficiency in high-dimensional spaces. By learning invertible transformations, flows enable exact density estimation while mitigating the instability inherent in distance-based methods. We provide theoretical guarantees showing that our estimation error depends on the data{'}s intrinsic structure rather than its raw dimensionality. Experiments across 11 datasets demonstrate that FLARE achieves a strong Spearman{'}s {\ensuremath{\rho}} (up to 0.90) with supervised benchmarks, remaining robust even for high-dimensional embeddings (d {\ensuremath{\geq}} 3,584)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2026-flare">
<titleInfo>
<title>FLARE: Task-Agnostic Embedding Model Evaluation via Normalizing Flows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingzhou</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kar</namePart>
<namePart type="given">Yan</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Despite the widespread adoption of text embedding models, selecting the optimal model for a specific target corpus remains challenging due to the lack of task-specific labels. While task-agnostic evaluation offers a promising solution by relying on unlabeled data, existing approaches based on kernel estimators or Gaussian mixtures fail to model high-dimensional distributions effectively, resulting in unstable rankings. To address this limitation, we propose FLARE (Flow-based Label-free Assessment of Representation Embeddings), which employs normalizing flows to estimate information sufficiency in high-dimensional spaces. By learning invertible transformations, flows enable exact density estimation while mitigating the instability inherent in distance-based methods. We provide theoretical guarantees showing that our estimation error depends on the data’s intrinsic structure rather than its raw dimensionality. Experiments across 11 datasets demonstrate that FLARE achieves a strong Spearman’s \ensuremathρ (up to 0.90) with supervised benchmarks, remaining robust even for high-dimensional embeddings (d \ensuremath\geq 3,584).</abstract>
<identifier type="citekey">jiang-etal-2026-flare</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1957</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1957/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>39271</start>
<end>39294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FLARE: Task-Agnostic Embedding Model Evaluation via Normalizing Flows
%A Jiang, Jingzhou
%A Tang, Yixuan
%A Yang, Yi
%A Tam, Kar Yan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F jiang-etal-2026-flare
%X Despite the widespread adoption of text embedding models, selecting the optimal model for a specific target corpus remains challenging due to the lack of task-specific labels. While task-agnostic evaluation offers a promising solution by relying on unlabeled data, existing approaches based on kernel estimators or Gaussian mixtures fail to model high-dimensional distributions effectively, resulting in unstable rankings. To address this limitation, we propose FLARE (Flow-based Label-free Assessment of Representation Embeddings), which employs normalizing flows to estimate information sufficiency in high-dimensional spaces. By learning invertible transformations, flows enable exact density estimation while mitigating the instability inherent in distance-based methods. We provide theoretical guarantees showing that our estimation error depends on the data’s intrinsic structure rather than its raw dimensionality. Experiments across 11 datasets demonstrate that FLARE achieves a strong Spearman’s \ensuremathρ (up to 0.90) with supervised benchmarks, remaining robust even for high-dimensional embeddings (d \ensuremath\geq 3,584).
%R 10.18653/v1/2026.findings-acl.1957
%U https://aclanthology.org/2026.findings-acl.1957/
%U https://doi.org/10.18653/v1/2026.findings-acl.1957
%P 39271-39294
Markdown (Informal)
[FLARE: Task-Agnostic Embedding Model Evaluation via Normalizing Flows](https://aclanthology.org/2026.findings-acl.1957/) (Jiang et al., Findings 2026)
ACL