@inproceedings{schouten-bloem-2026-probing,
title = "Probing Without Labels: Contrast-only Reproductions of Interpretability Results",
author = "Schouten, Stefan F. and
Bloem, Peter",
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-1.67/",
pages = "1167--1183",
ISBN = "979-8-89176-476-7",
abstract = "Contrastive interpretability methods use pairs (or tuples) of inputs whose elements differ in minimal but controlled ways. Contrast-Consistent Search (CCS) is one such method that can identify whether (language) models encode binary features, such as sentence truth, in their internal activations. One advantage is that this requires no labels, meaning there is no assumption that internal activations agree with those labels, as is the case for supervised methods. In this work, we (1) reproduce results previously obtained with CCS, (2) better understand CCS{'}s objective, (3) propose Tuple-Contrastive PCA (tcPCA), a method with closed-form solutions, as a spiritual successor, and (4) show how tcPCA has wider applicability than CCS by: allowing for n-ary rather than just binary variables; and, finding contrastive subspaces instead of directions. See https://contrast.stefanfs.me for code and interactive figures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schouten-bloem-2026-probing">
<titleInfo>
<title>Probing Without Labels: Contrast-only Reproductions of Interpretability Results</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Schouten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bloem</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>Contrastive interpretability methods use pairs (or tuples) of inputs whose elements differ in minimal but controlled ways. Contrast-Consistent Search (CCS) is one such method that can identify whether (language) models encode binary features, such as sentence truth, in their internal activations. One advantage is that this requires no labels, meaning there is no assumption that internal activations agree with those labels, as is the case for supervised methods. In this work, we (1) reproduce results previously obtained with CCS, (2) better understand CCS’s objective, (3) propose Tuple-Contrastive PCA (tcPCA), a method with closed-form solutions, as a spiritual successor, and (4) show how tcPCA has wider applicability than CCS by: allowing for n-ary rather than just binary variables; and, finding contrastive subspaces instead of directions. See https://contrast.stefanfs.me for code and interactive figures.</abstract>
<identifier type="citekey">schouten-bloem-2026-probing</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.67/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1167</start>
<end>1183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing Without Labels: Contrast-only Reproductions of Interpretability Results
%A Schouten, Stefan F.
%A Bloem, Peter
%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 schouten-bloem-2026-probing
%X Contrastive interpretability methods use pairs (or tuples) of inputs whose elements differ in minimal but controlled ways. Contrast-Consistent Search (CCS) is one such method that can identify whether (language) models encode binary features, such as sentence truth, in their internal activations. One advantage is that this requires no labels, meaning there is no assumption that internal activations agree with those labels, as is the case for supervised methods. In this work, we (1) reproduce results previously obtained with CCS, (2) better understand CCS’s objective, (3) propose Tuple-Contrastive PCA (tcPCA), a method with closed-form solutions, as a spiritual successor, and (4) show how tcPCA has wider applicability than CCS by: allowing for n-ary rather than just binary variables; and, finding contrastive subspaces instead of directions. See https://contrast.stefanfs.me for code and interactive figures.
%U https://aclanthology.org/2026.blackboxnlp-1.67/
%P 1167-1183
Markdown (Informal)
[Probing Without Labels: Contrast-only Reproductions of Interpretability Results](https://aclanthology.org/2026.blackboxnlp-1.67/) (Schouten & Bloem, BlackboxNLP 2026)
ACL