@inproceedings{nikankin-etal-2025-blackboxnlp,
title = "{B}lackbox{NLP}-2025 {MIB} Shared Task: Improving Circuit Faithfulness via Better Edge Selection",
author = "Nikankin, Yaniv and
Arad, Dana and
Itzhak, Itay and
Reusch, Anja and
Simhi, Adi and
Kesten, Gal and
Belinkov, Yonatan",
editor = "Belinkov, Yonatan and
Mueller, Aaron and
Kim, Najoung and
Mohebbi, Hosein and
Chen, Hanjie and
Arad, Dana and
Sarti, Gabriele",
booktitle = "Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.blackboxnlp-1.29/",
pages = "521--527",
ISBN = "979-8-89176-346-3",
abstract = "One of the main challenges in mechanistic interpretability is circuit discovery {--} determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikankin-etal-2025-blackboxnlp">
<titleInfo>
<title>BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaniv</namePart>
<namePart type="family">Nikankin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Itzhak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anja</namePart>
<namePart type="family">Reusch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adi</namePart>
<namePart type="family">Simhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gal</namePart>
<namePart type="family">Kesten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<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">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najoung</namePart>
<namePart type="family">Kim</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">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-346-3</identifier>
</relatedItem>
<abstract>One of the main challenges in mechanistic interpretability is circuit discovery – determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models.</abstract>
<identifier type="citekey">nikankin-etal-2025-blackboxnlp</identifier>
<location>
<url>https://aclanthology.org/2025.blackboxnlp-1.29/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>521</start>
<end>527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
%A Nikankin, Yaniv
%A Arad, Dana
%A Itzhak, Itay
%A Reusch, Anja
%A Simhi, Adi
%A Kesten, Gal
%A Belinkov, Yonatan
%Y Belinkov, Yonatan
%Y Mueller, Aaron
%Y Kim, Najoung
%Y Mohebbi, Hosein
%Y Chen, Hanjie
%Y Arad, Dana
%Y Sarti, Gabriele
%S Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-346-3
%F nikankin-etal-2025-blackboxnlp
%X One of the main challenges in mechanistic interpretability is circuit discovery – determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models.
%U https://aclanthology.org/2025.blackboxnlp-1.29/
%P 521-527
Markdown (Informal)
[BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection](https://aclanthology.org/2025.blackboxnlp-1.29/) (Nikankin et al., BlackboxNLP 2025)
ACL