@inproceedings{azarkhalili-etal-2026-pr,
title = "{PR}-{XAI}: {P}age{R}ank-Based Feature Attribution for Transformers",
author = "Azarkhalili, Behrooz and
Li, Linyi and
Libbrecht, Maxwell W.",
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.22/",
pages = "534--554",
ISBN = "979-8-89176-390-6",
abstract = "We introduce PR-XAI, a feature attribution method for transformer models based on the PageRank algorithm. The proposed PR-XAI models the attention mechanism as a directed graph, with weights derived from attention weights and their gradients. Evaluations across five well-known text classification datasets and three different architectures show that PR-AG, one variant of PR-XAI, outperforms state-of-the-art attribution methods in faithfulness and classification metrics, with significant gains on long-form text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azarkhalili-etal-2026-pr">
<titleInfo>
<title>PR-XAI: PageRank-Based Feature Attribution for Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behrooz</namePart>
<namePart type="family">Azarkhalili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxwell</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Libbrecht</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 introduce PR-XAI, a feature attribution method for transformer models based on the PageRank algorithm. The proposed PR-XAI models the attention mechanism as a directed graph, with weights derived from attention weights and their gradients. Evaluations across five well-known text classification datasets and three different architectures show that PR-AG, one variant of PR-XAI, outperforms state-of-the-art attribution methods in faithfulness and classification metrics, with significant gains on long-form text.</abstract>
<identifier type="citekey">azarkhalili-etal-2026-pr</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.22/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>534</start>
<end>554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PR-XAI: PageRank-Based Feature Attribution for Transformers
%A Azarkhalili, Behrooz
%A Li, Linyi
%A Libbrecht, Maxwell W.
%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 azarkhalili-etal-2026-pr
%X We introduce PR-XAI, a feature attribution method for transformer models based on the PageRank algorithm. The proposed PR-XAI models the attention mechanism as a directed graph, with weights derived from attention weights and their gradients. Evaluations across five well-known text classification datasets and three different architectures show that PR-AG, one variant of PR-XAI, outperforms state-of-the-art attribution methods in faithfulness and classification metrics, with significant gains on long-form text.
%U https://aclanthology.org/2026.acl-long.22/
%P 534-554
Markdown (Informal)
[PR-XAI: PageRank-Based Feature Attribution for Transformers](https://aclanthology.org/2026.acl-long.22/) (Azarkhalili et al., ACL 2026)
ACL
- Behrooz Azarkhalili, Linyi Li, and Maxwell W. Libbrecht. 2026. PR-XAI: PageRank-Based Feature Attribution for Transformers. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 534–554, San Diego, California, United States. Association for Computational Linguistics.