@inproceedings{kim-etal-2026-listwise,
title = "Listwise Explanation of Embedding-Based Rankings via Semantic Chunk Grouping",
author = "Kim, Hyunkyu and
Yoo, Yeeun and
Kwak, Youngjun",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2230/",
pages = "47743--47761",
ISBN = "979-8-89176-462-0",
abstract = "Dense embedding rankers score documents through contextual sentence- and passage-level representations, yet listwise explanation methods often attribute rankings to isolated words. We study this mismatch and introduce ChunkGroupSHAP, a listwise Shapley method that clusters semantically related chunks across documents into shared features, preserving contextual evidence while bounding the KernelSHAP regression dimension by the group count. Across MS MARCO, FinanceBench, AILACaseDocs, and FinQA with E5-family rankers and BM25, raw chunks improve rank-reconstruction Fidelity over RankSHAP{'}s word features in all 11 dense-ranker settings. The best chunk-group configuration further improves on raw chunks in eight of these settings, with the incremental benefit depending on grouping scope; word features remain strongest in three of four BM25 settings. These results show that explanation units should match the ranking model: contextual chunks better suit dense bi-encoders, whereas words remain effective for BM25. ChunkGroupSHAP supports listwise attribution over contextual evidence through a bounded feature space shared across documents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-listwise">
<titleInfo>
<title>Listwise Explanation of Embedding-Based Rankings via Semantic Chunk Grouping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyunkyu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeeun</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngjun</namePart>
<namePart type="family">Kwak</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Dense embedding rankers score documents through contextual sentence- and passage-level representations, yet listwise explanation methods often attribute rankings to isolated words. We study this mismatch and introduce ChunkGroupSHAP, a listwise Shapley method that clusters semantically related chunks across documents into shared features, preserving contextual evidence while bounding the KernelSHAP regression dimension by the group count. Across MS MARCO, FinanceBench, AILACaseDocs, and FinQA with E5-family rankers and BM25, raw chunks improve rank-reconstruction Fidelity over RankSHAP’s word features in all 11 dense-ranker settings. The best chunk-group configuration further improves on raw chunks in eight of these settings, with the incremental benefit depending on grouping scope; word features remain strongest in three of four BM25 settings. These results show that explanation units should match the ranking model: contextual chunks better suit dense bi-encoders, whereas words remain effective for BM25. ChunkGroupSHAP supports listwise attribution over contextual evidence through a bounded feature space shared across documents.</abstract>
<identifier type="citekey">kim-etal-2026-listwise</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2230/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47743</start>
<end>47761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Listwise Explanation of Embedding-Based Rankings via Semantic Chunk Grouping
%A Kim, Hyunkyu
%A Yoo, Yeeun
%A Kwak, Youngjun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kim-etal-2026-listwise
%X Dense embedding rankers score documents through contextual sentence- and passage-level representations, yet listwise explanation methods often attribute rankings to isolated words. We study this mismatch and introduce ChunkGroupSHAP, a listwise Shapley method that clusters semantically related chunks across documents into shared features, preserving contextual evidence while bounding the KernelSHAP regression dimension by the group count. Across MS MARCO, FinanceBench, AILACaseDocs, and FinQA with E5-family rankers and BM25, raw chunks improve rank-reconstruction Fidelity over RankSHAP’s word features in all 11 dense-ranker settings. The best chunk-group configuration further improves on raw chunks in eight of these settings, with the incremental benefit depending on grouping scope; word features remain strongest in three of four BM25 settings. These results show that explanation units should match the ranking model: contextual chunks better suit dense bi-encoders, whereas words remain effective for BM25. ChunkGroupSHAP supports listwise attribution over contextual evidence through a bounded feature space shared across documents.
%U https://aclanthology.org/2026.findings-emnlp.2230/
%P 47743-47761
Markdown (Informal)
[Listwise Explanation of Embedding-Based Rankings via Semantic Chunk Grouping](https://aclanthology.org/2026.findings-emnlp.2230/) (Kim et al., Findings 2026)
ACL