@inproceedings{long-etal-2026-rebound,
title = "{R}e{B}ound: Relevance-Boundary Supervision for Distractor-Robust Mathematical Reasoning",
author = "Long, Jiahui and
Shou, Lidan and
Li, Huan and
Chen, Ke",
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.2402/",
pages = "51612--51627",
ISBN = "979-8-89176-462-0",
abstract = "Mathematical word problems with plausible irrelevant context expose a failure mode in which language models reason from facts that should not support the target solution. We formulate distractor-robust mathematical reasoning as relevance-boundary supervision: a model should separate Signal facts from Distractor facts before solving, and then ground the solution in Signal facts only. We introduce ReBound, a post-training framework that constructs paired clean{--}distractor examples, trains boundary-first traces with supervised fine-tuning, and applies correctness-guided reinforcement learning to discourage Distractor use. Across three open base LLMs and six mathematical reasoning benchmarks, ReBound consistently improves distractor robustness over CoT prompting and strong training-based baselines; on Qwen3-0.6B, the distractor benchmark average increases from 34.92 to 48.29. ReBound also preserves competitive clean and perturbation performance. Process diagnostics, ablations, and output-length analysis show that these gains are tied to better fact use and boundary behavior, rather than longer generations or answer-only optimization.The code is available at https://anonymous.4open.science/r/Rebound-5FB8"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2026-rebound">
<titleInfo>
<title>ReBound: Relevance-Boundary Supervision for Distractor-Robust Mathematical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiahui</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidan</namePart>
<namePart type="family">Shou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Chen</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>Mathematical word problems with plausible irrelevant context expose a failure mode in which language models reason from facts that should not support the target solution. We formulate distractor-robust mathematical reasoning as relevance-boundary supervision: a model should separate Signal facts from Distractor facts before solving, and then ground the solution in Signal facts only. We introduce ReBound, a post-training framework that constructs paired clean–distractor examples, trains boundary-first traces with supervised fine-tuning, and applies correctness-guided reinforcement learning to discourage Distractor use. Across three open base LLMs and six mathematical reasoning benchmarks, ReBound consistently improves distractor robustness over CoT prompting and strong training-based baselines; on Qwen3-0.6B, the distractor benchmark average increases from 34.92 to 48.29. ReBound also preserves competitive clean and perturbation performance. Process diagnostics, ablations, and output-length analysis show that these gains are tied to better fact use and boundary behavior, rather than longer generations or answer-only optimization.The code is available at https://anonymous.4open.science/r/Rebound-5FB8</abstract>
<identifier type="citekey">long-etal-2026-rebound</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2402/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51612</start>
<end>51627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReBound: Relevance-Boundary Supervision for Distractor-Robust Mathematical Reasoning
%A Long, Jiahui
%A Shou, Lidan
%A Li, Huan
%A Chen, Ke
%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 long-etal-2026-rebound
%X Mathematical word problems with plausible irrelevant context expose a failure mode in which language models reason from facts that should not support the target solution. We formulate distractor-robust mathematical reasoning as relevance-boundary supervision: a model should separate Signal facts from Distractor facts before solving, and then ground the solution in Signal facts only. We introduce ReBound, a post-training framework that constructs paired clean–distractor examples, trains boundary-first traces with supervised fine-tuning, and applies correctness-guided reinforcement learning to discourage Distractor use. Across three open base LLMs and six mathematical reasoning benchmarks, ReBound consistently improves distractor robustness over CoT prompting and strong training-based baselines; on Qwen3-0.6B, the distractor benchmark average increases from 34.92 to 48.29. ReBound also preserves competitive clean and perturbation performance. Process diagnostics, ablations, and output-length analysis show that these gains are tied to better fact use and boundary behavior, rather than longer generations or answer-only optimization.The code is available at https://anonymous.4open.science/r/Rebound-5FB8
%U https://aclanthology.org/2026.findings-emnlp.2402/
%P 51612-51627
Markdown (Informal)
[ReBound: Relevance-Boundary Supervision for Distractor-Robust Mathematical Reasoning](https://aclanthology.org/2026.findings-emnlp.2402/) (Long et al., Findings 2026)
ACL