@inproceedings{ferner-wegenkittl-2026-lost,
title = "Lost in Specialization: Embedding Geometry and Retrieval Quality Across Specialized Corpora",
author = "Ferner, Cornelia and
Wegenkittl, Stefan",
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.4/",
pages = "49--57",
ISBN = "979-8-89176-476-7",
abstract = "Reliably operating LLMs in specialized domains often requires retrieval-augmented generation (RAG), which grounds the model{'}s responses in domain-specific information. Retrieval performance is critical for output quality, making retrieval model selection a key decision for specialized RAG deployments. To guide retrieval model selection, we ask whether domain-tuned encoders produce better-structured embedding spaces for specialized corpora than general-purpose encoders, and whether geometric regularity alone reliably indicates retrieval quality in these settings. Our results show that the answer is more nuanced than expected: domain-specific models show more pronounced geometric irregularity than general-domain encoders, while geometric regularity alone does not reliably indicate retrieval quality. Moreover, geometric and intervention patterns observed on MS-MARCO do not consistently transfer to specialized corpora."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferner-wegenkittl-2026-lost">
<titleInfo>
<title>Lost in Specialization: Embedding Geometry and Retrieval Quality Across Specialized Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Ferner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Wegenkittl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Reliably operating LLMs in specialized domains often requires retrieval-augmented generation (RAG), which grounds the model’s responses in domain-specific information. Retrieval performance is critical for output quality, making retrieval model selection a key decision for specialized RAG deployments. To guide retrieval model selection, we ask whether domain-tuned encoders produce better-structured embedding spaces for specialized corpora than general-purpose encoders, and whether geometric regularity alone reliably indicates retrieval quality in these settings. Our results show that the answer is more nuanced than expected: domain-specific models show more pronounced geometric irregularity than general-domain encoders, while geometric regularity alone does not reliably indicate retrieval quality. Moreover, geometric and intervention patterns observed on MS-MARCO do not consistently transfer to specialized corpora.</abstract>
<identifier type="citekey">ferner-wegenkittl-2026-lost</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.4/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>49</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost in Specialization: Embedding Geometry and Retrieval Quality Across Specialized Corpora
%A Ferner, Cornelia
%A Wegenkittl, Stefan
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F ferner-wegenkittl-2026-lost
%X Reliably operating LLMs in specialized domains often requires retrieval-augmented generation (RAG), which grounds the model’s responses in domain-specific information. Retrieval performance is critical for output quality, making retrieval model selection a key decision for specialized RAG deployments. To guide retrieval model selection, we ask whether domain-tuned encoders produce better-structured embedding spaces for specialized corpora than general-purpose encoders, and whether geometric regularity alone reliably indicates retrieval quality in these settings. Our results show that the answer is more nuanced than expected: domain-specific models show more pronounced geometric irregularity than general-domain encoders, while geometric regularity alone does not reliably indicate retrieval quality. Moreover, geometric and intervention patterns observed on MS-MARCO do not consistently transfer to specialized corpora.
%U https://aclanthology.org/2026.blackboxnlp-1.4/
%P 49-57
Markdown (Informal)
[Lost in Specialization: Embedding Geometry and Retrieval Quality Across Specialized Corpora](https://aclanthology.org/2026.blackboxnlp-1.4/) (Ferner & Wegenkittl, BlackboxNLP 2026)
ACL