@inproceedings{polyakova-etal-2026-claude,
title = "{C}laude reinvestigates herself: A replication of different types of syntactic agreement recruit the same units in {LLM}s",
author = "Polyakova, Elena and
Arora, Shivan and
Salhan, Suchir and
Buttery, Paula",
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-1.69/",
pages = "1196--1222",
ISBN = "979-8-89176-476-7",
abstract = "The representation of grammatical knowledge in individual LLM neurons and attention heads remains poorly understood. We replicate the feature-based approach of Kryvosheieva et al. (2026) that uses functional localisation to illustrate that distinct syntactic phenomena can recruit the same units. We reproduce and extend the paper to new minimal pair datasets (Dutch, Turkish, and Russian) and additional interpretability techniques: Attention-based analysis, Differential Binary Masking (DBM), and Distributed Alignment Search (DAS). We find reproducible and robust evidence for syntactic localisation in LLMs across several methods and languages. However, localisation strength depends on interpretability techniques (particularly for DBM) and varies across languages, highlighting the value of validating mechanistic claims using several techniques. Code and data available via https://anonymous.4open.science/r/syntax-interpretability-F4C3"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="polyakova-etal-2026-claude">
<titleInfo>
<title>Claude reinvestigates herself: A replication of different types of syntactic agreement recruit the same units in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Polyakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivan</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchir</namePart>
<namePart type="family">Salhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</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>The representation of grammatical knowledge in individual LLM neurons and attention heads remains poorly understood. We replicate the feature-based approach of Kryvosheieva et al. (2026) that uses functional localisation to illustrate that distinct syntactic phenomena can recruit the same units. We reproduce and extend the paper to new minimal pair datasets (Dutch, Turkish, and Russian) and additional interpretability techniques: Attention-based analysis, Differential Binary Masking (DBM), and Distributed Alignment Search (DAS). We find reproducible and robust evidence for syntactic localisation in LLMs across several methods and languages. However, localisation strength depends on interpretability techniques (particularly for DBM) and varies across languages, highlighting the value of validating mechanistic claims using several techniques. Code and data available via https://anonymous.4open.science/r/syntax-interpretability-F4C3</abstract>
<identifier type="citekey">polyakova-etal-2026-claude</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.69/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1196</start>
<end>1222</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Claude reinvestigates herself: A replication of different types of syntactic agreement recruit the same units in LLMs
%A Polyakova, Elena
%A Arora, Shivan
%A Salhan, Suchir
%A Buttery, Paula
%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 polyakova-etal-2026-claude
%X The representation of grammatical knowledge in individual LLM neurons and attention heads remains poorly understood. We replicate the feature-based approach of Kryvosheieva et al. (2026) that uses functional localisation to illustrate that distinct syntactic phenomena can recruit the same units. We reproduce and extend the paper to new minimal pair datasets (Dutch, Turkish, and Russian) and additional interpretability techniques: Attention-based analysis, Differential Binary Masking (DBM), and Distributed Alignment Search (DAS). We find reproducible and robust evidence for syntactic localisation in LLMs across several methods and languages. However, localisation strength depends on interpretability techniques (particularly for DBM) and varies across languages, highlighting the value of validating mechanistic claims using several techniques. Code and data available via https://anonymous.4open.science/r/syntax-interpretability-F4C3
%U https://aclanthology.org/2026.blackboxnlp-1.69/
%P 1196-1222
Markdown (Informal)
[Claude reinvestigates herself: A replication of different types of syntactic agreement recruit the same units in LLMs](https://aclanthology.org/2026.blackboxnlp-1.69/) (Polyakova et al., BlackboxNLP 2026)
ACL