@inproceedings{li-etal-2026-retre,
title = "{R}e{TRE}: Benchmarking {LLM} Transfer Robustness with Structure-Preserving Variants",
author = "Li, ZhongDong and
Shi, Weijie and
Cui, Yue and
MA, Haolun and
Liu, Yuanjun and
Li, Jiawei and
Liu, An and
Zhu, Jia and
Xu, Jiajie",
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.2048/",
pages = "44257--44268",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) have achieved strong performance on standard benchmarks, yet their performance is not robust across different task manifestations. It remains unclear how performance changes under controlled task rewrites that preserve the original solution structure, while varying the rewrite type and level. To address this question, we introduce ReTRE (Rewrite-based Transfer Robustness Evaluation), an evaluation benchmark inspired by learning transfer theory that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer. ReTRE employs a multi-agent system to construct textual and visual variants while preserving the structure of the original solution. Evaluations on mathematical and science tasks across state-of-the-art multimodal LLMs reveal a consistent transfer gap: performance exhibits a general declining trend as transfer similarity drops and strong text performance can face performance decline under cross-modal transfer. Crucially, we identify a divergence between post-training paradigms: reinforcement learning preserves transfer robustness, whereas supervised fine-tuning tends to overfit the training distribution, leading to severe degradation in far-transfer performance despite strong in-distribution accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-retre">
<titleInfo>
<title>ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants</title>
</titleInfo>
<name type="personal">
<namePart type="given">ZhongDong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haolun</namePart>
<namePart type="family">MA</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanjun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajie</namePart>
<namePart type="family">Xu</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>Large language models (LLMs) have achieved strong performance on standard benchmarks, yet their performance is not robust across different task manifestations. It remains unclear how performance changes under controlled task rewrites that preserve the original solution structure, while varying the rewrite type and level. To address this question, we introduce ReTRE (Rewrite-based Transfer Robustness Evaluation), an evaluation benchmark inspired by learning transfer theory that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer. ReTRE employs a multi-agent system to construct textual and visual variants while preserving the structure of the original solution. Evaluations on mathematical and science tasks across state-of-the-art multimodal LLMs reveal a consistent transfer gap: performance exhibits a general declining trend as transfer similarity drops and strong text performance can face performance decline under cross-modal transfer. Crucially, we identify a divergence between post-training paradigms: reinforcement learning preserves transfer robustness, whereas supervised fine-tuning tends to overfit the training distribution, leading to severe degradation in far-transfer performance despite strong in-distribution accuracy.</abstract>
<identifier type="citekey">li-etal-2026-retre</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2048/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>44257</start>
<end>44268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants
%A Li, ZhongDong
%A Shi, Weijie
%A Cui, Yue
%A MA, Haolun
%A Liu, Yuanjun
%A Li, Jiawei
%A Liu, An
%A Zhu, Jia
%A Xu, Jiajie
%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 li-etal-2026-retre
%X Large language models (LLMs) have achieved strong performance on standard benchmarks, yet their performance is not robust across different task manifestations. It remains unclear how performance changes under controlled task rewrites that preserve the original solution structure, while varying the rewrite type and level. To address this question, we introduce ReTRE (Rewrite-based Transfer Robustness Evaluation), an evaluation benchmark inspired by learning transfer theory that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer. ReTRE employs a multi-agent system to construct textual and visual variants while preserving the structure of the original solution. Evaluations on mathematical and science tasks across state-of-the-art multimodal LLMs reveal a consistent transfer gap: performance exhibits a general declining trend as transfer similarity drops and strong text performance can face performance decline under cross-modal transfer. Crucially, we identify a divergence between post-training paradigms: reinforcement learning preserves transfer robustness, whereas supervised fine-tuning tends to overfit the training distribution, leading to severe degradation in far-transfer performance despite strong in-distribution accuracy.
%U https://aclanthology.org/2026.acl-long.2048/
%P 44257-44268
Markdown (Informal)
[ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants](https://aclanthology.org/2026.acl-long.2048/) (Li et al., ACL 2026)
ACL
- ZhongDong Li, Weijie Shi, Yue Cui, Haolun MA, Yuanjun Liu, Jiawei Li, An Liu, Jia Zhu, and Jiajie Xu. 2026. ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 44257–44268, San Diego, California, United States. Association for Computational Linguistics.