@inproceedings{vujanic-ruckstiess-2026-leaf,
title = "{LEAF}: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations",
author = {Vujanic, Robin and
R{\"u}ckstie{\ss}, Thomas},
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2008/",
doi = "10.18653/v1/2026.acl-long.2008",
pages = "43362--43383",
ISBN = "979-8-89176-390-6",
abstract = "We present a knowledge distillation framework for text embedding models. A key distinguishing feature is that our distilled models are compatible with their teacher, enabling flexible asymmetric architectures where documents are encoded with the larger teacher model, while queries use smaller student models. We also show that our models automatically inherit MRL and robustness to output quantization whenever these properties are present in the teacher model, without explicitly training for them. To demonstrate the effectiveness of our framework we publish leaf-ir, a 23M parameters information retrieval oriented model that, besides being teacher-compatibile, sets a new state-of-the-art (SOTA) on BEIR, ranking no.1 on the public leaderboard for models of its size. Asymmetric mode further increases its retrieval performance. Our scheme is however not restricted to information retrieval. We demonstrate its wider applicability by synthesizing the multi-task leaf-mt model. This also sets a new SOTA, achieving no.1 on the public MTEB v2 (English) leaderboard for models of its size. Our technique is applicable to black-box models, requires no judgments nor hard negatives, and training can be conducted using small batch sizes. Thus, dataset and training infrastructure requirements for our framework are modest. We make our models publicly available under a permissive Apache 2.0 license."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vujanic-ruckstiess-2026-leaf">
<titleInfo>
<title>LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Vujanic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Rückstieß</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>We present a knowledge distillation framework for text embedding models. A key distinguishing feature is that our distilled models are compatible with their teacher, enabling flexible asymmetric architectures where documents are encoded with the larger teacher model, while queries use smaller student models. We also show that our models automatically inherit MRL and robustness to output quantization whenever these properties are present in the teacher model, without explicitly training for them. To demonstrate the effectiveness of our framework we publish leaf-ir, a 23M parameters information retrieval oriented model that, besides being teacher-compatibile, sets a new state-of-the-art (SOTA) on BEIR, ranking no.1 on the public leaderboard for models of its size. Asymmetric mode further increases its retrieval performance. Our scheme is however not restricted to information retrieval. We demonstrate its wider applicability by synthesizing the multi-task leaf-mt model. This also sets a new SOTA, achieving no.1 on the public MTEB v2 (English) leaderboard for models of its size. Our technique is applicable to black-box models, requires no judgments nor hard negatives, and training can be conducted using small batch sizes. Thus, dataset and training infrastructure requirements for our framework are modest. We make our models publicly available under a permissive Apache 2.0 license.</abstract>
<identifier type="citekey">vujanic-ruckstiess-2026-leaf</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.2008</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2008/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>43362</start>
<end>43383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
%A Vujanic, Robin
%A Rückstieß, Thomas
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F vujanic-ruckstiess-2026-leaf
%X We present a knowledge distillation framework for text embedding models. A key distinguishing feature is that our distilled models are compatible with their teacher, enabling flexible asymmetric architectures where documents are encoded with the larger teacher model, while queries use smaller student models. We also show that our models automatically inherit MRL and robustness to output quantization whenever these properties are present in the teacher model, without explicitly training for them. To demonstrate the effectiveness of our framework we publish leaf-ir, a 23M parameters information retrieval oriented model that, besides being teacher-compatibile, sets a new state-of-the-art (SOTA) on BEIR, ranking no.1 on the public leaderboard for models of its size. Asymmetric mode further increases its retrieval performance. Our scheme is however not restricted to information retrieval. We demonstrate its wider applicability by synthesizing the multi-task leaf-mt model. This also sets a new SOTA, achieving no.1 on the public MTEB v2 (English) leaderboard for models of its size. Our technique is applicable to black-box models, requires no judgments nor hard negatives, and training can be conducted using small batch sizes. Thus, dataset and training infrastructure requirements for our framework are modest. We make our models publicly available under a permissive Apache 2.0 license.
%R 10.18653/v1/2026.acl-long.2008
%U https://aclanthology.org/2026.acl-long.2008/
%U https://doi.org/10.18653/v1/2026.acl-long.2008
%P 43362-43383
Markdown (Informal)
[LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations](https://aclanthology.org/2026.acl-long.2008/) (Vujanic & Rückstieß, ACL 2026)
ACL