@inproceedings{feng-etal-2026-sumrank,
title = "{S}um{R}ank: Aligning Summarization Models for Long-Document Listwise Reranking",
author = "Feng, Jincheng and
Liu, Wenhan and
Dou, Zhicheng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1451/",
pages = "33129--33156",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and efficiency issues due to the substantially increased context length. To address this challenge, we propose a per-document summarization model SumRank, aligned with downstream listwise reranking, to compress long-form documents into concise rank-aligned summaries before the final listwise reranking stage. To develop our summarization model SumRank, we introduce a three-stage training pipeline consisting of cold-start Supervised Fine-Tuning (SFT), specialized Reinforcement Learning (RL) data construction, and rank-driven alignment via RL. This paradigm aligns the SumRank with downstream ranking objectives to preserve crucial relevance signals. We conduct extensive experiments on both in-domain (ID) benchmark datasets from the TREC Deep Learning tracks and out-of-domain (OOD) datasets from the BEIR benchmark. Results show that our lightweight SumRank model achieves state-of-the-art (SOTA) ranking performance while significantly improving efficiency by reducing both summarization overhead and reranking complexity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2026-sumrank">
<titleInfo>
<title>SumRank: Aligning Summarization Models for Long-Document Listwise Reranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jincheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Dou</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and efficiency issues due to the substantially increased context length. To address this challenge, we propose a per-document summarization model SumRank, aligned with downstream listwise reranking, to compress long-form documents into concise rank-aligned summaries before the final listwise reranking stage. To develop our summarization model SumRank, we introduce a three-stage training pipeline consisting of cold-start Supervised Fine-Tuning (SFT), specialized Reinforcement Learning (RL) data construction, and rank-driven alignment via RL. This paradigm aligns the SumRank with downstream ranking objectives to preserve crucial relevance signals. We conduct extensive experiments on both in-domain (ID) benchmark datasets from the TREC Deep Learning tracks and out-of-domain (OOD) datasets from the BEIR benchmark. Results show that our lightweight SumRank model achieves state-of-the-art (SOTA) ranking performance while significantly improving efficiency by reducing both summarization overhead and reranking complexity.</abstract>
<identifier type="citekey">feng-etal-2026-sumrank</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1451/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33129</start>
<end>33156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SumRank: Aligning Summarization Models for Long-Document Listwise Reranking
%A Feng, Jincheng
%A Liu, Wenhan
%A Dou, Zhicheng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F feng-etal-2026-sumrank
%X Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and efficiency issues due to the substantially increased context length. To address this challenge, we propose a per-document summarization model SumRank, aligned with downstream listwise reranking, to compress long-form documents into concise rank-aligned summaries before the final listwise reranking stage. To develop our summarization model SumRank, we introduce a three-stage training pipeline consisting of cold-start Supervised Fine-Tuning (SFT), specialized Reinforcement Learning (RL) data construction, and rank-driven alignment via RL. This paradigm aligns the SumRank with downstream ranking objectives to preserve crucial relevance signals. We conduct extensive experiments on both in-domain (ID) benchmark datasets from the TREC Deep Learning tracks and out-of-domain (OOD) datasets from the BEIR benchmark. Results show that our lightweight SumRank model achieves state-of-the-art (SOTA) ranking performance while significantly improving efficiency by reducing both summarization overhead and reranking complexity.
%U https://aclanthology.org/2026.emnlp-main.1451/
%P 33129-33156
Markdown (Informal)
[SumRank: Aligning Summarization Models for Long-Document Listwise Reranking](https://aclanthology.org/2026.emnlp-main.1451/) (Feng et al., EMNLP 2026)
ACL