@inproceedings{cao-etal-2026-re3,
title = "Re$^3$: Relevance {\&} Recency Retrieval for Mitigating Temporal Hallucination",
author = "Cao, Jiawei and
Ouyang, Jie and
Cheng, Mingyue and
Zhou, Zhaomeng and
Liu, Chunli and
Li, Yupeng and
Liu, Zirui and
Wang, Shijin",
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.1180/",
pages = "25735--25760",
ISBN = "979-8-89176-390-6",
abstract = "Retrieval-Augmented Generation (RAG) is a mainstream approach to mitigating hallucinations in Large Language Models (LLMs), yet in dynamic real-world scenarios, such as weather forecasting or evolving news events, existing retrievers suffer from both temporal-semantic misalignment and outdated-document interference. To address this, we propose Relevance Recency Retrieval (Re$^3$), a novel framework that mitigates temporal hallucinations via two core components: a Time-Aware Dual Relevance Encoder that embeds heterogeneous temporal signals into the semantic space to ensure retrieval fidelity, and a Conflict-Aware Recency Filter that performs listwise arbitration to identify and suppress obsolete factual versions. To rigorously evaluate this setting, we introduce Re$^2$ Bench, a large-scale benchmark comprising over 1.3 million instances designed to assess system robustness in realistic environments where temporal constraints and conflicting factual versions coexist. Experiments on three public benchmarks and Re$^2$ Bench demonstrate that Re$^3$ consistently outperforms the strongest baselines by an average of 9.7{\%} in generation accuracy, with gains of up to 25.2{\%} on challenging dynamic tasks, while demonstrating robustness across diverse RAG settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2026-re3">
<titleInfo>
<title>Re³: Relevance & Recency Retrieval for Mitigating Temporal Hallucination</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyue</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaomeng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunli</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yupeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zirui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</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>Retrieval-Augmented Generation (RAG) is a mainstream approach to mitigating hallucinations in Large Language Models (LLMs), yet in dynamic real-world scenarios, such as weather forecasting or evolving news events, existing retrievers suffer from both temporal-semantic misalignment and outdated-document interference. To address this, we propose Relevance Recency Retrieval (Re³), a novel framework that mitigates temporal hallucinations via two core components: a Time-Aware Dual Relevance Encoder that embeds heterogeneous temporal signals into the semantic space to ensure retrieval fidelity, and a Conflict-Aware Recency Filter that performs listwise arbitration to identify and suppress obsolete factual versions. To rigorously evaluate this setting, we introduce Re² Bench, a large-scale benchmark comprising over 1.3 million instances designed to assess system robustness in realistic environments where temporal constraints and conflicting factual versions coexist. Experiments on three public benchmarks and Re² Bench demonstrate that Re³ consistently outperforms the strongest baselines by an average of 9.7% in generation accuracy, with gains of up to 25.2% on challenging dynamic tasks, while demonstrating robustness across diverse RAG settings.</abstract>
<identifier type="citekey">cao-etal-2026-re3</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1180/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>25735</start>
<end>25760</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Re³: Relevance & Recency Retrieval for Mitigating Temporal Hallucination
%A Cao, Jiawei
%A Ouyang, Jie
%A Cheng, Mingyue
%A Zhou, Zhaomeng
%A Liu, Chunli
%A Li, Yupeng
%A Liu, Zirui
%A Wang, Shijin
%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 cao-etal-2026-re3
%X Retrieval-Augmented Generation (RAG) is a mainstream approach to mitigating hallucinations in Large Language Models (LLMs), yet in dynamic real-world scenarios, such as weather forecasting or evolving news events, existing retrievers suffer from both temporal-semantic misalignment and outdated-document interference. To address this, we propose Relevance Recency Retrieval (Re³), a novel framework that mitigates temporal hallucinations via two core components: a Time-Aware Dual Relevance Encoder that embeds heterogeneous temporal signals into the semantic space to ensure retrieval fidelity, and a Conflict-Aware Recency Filter that performs listwise arbitration to identify and suppress obsolete factual versions. To rigorously evaluate this setting, we introduce Re² Bench, a large-scale benchmark comprising over 1.3 million instances designed to assess system robustness in realistic environments where temporal constraints and conflicting factual versions coexist. Experiments on three public benchmarks and Re² Bench demonstrate that Re³ consistently outperforms the strongest baselines by an average of 9.7% in generation accuracy, with gains of up to 25.2% on challenging dynamic tasks, while demonstrating robustness across diverse RAG settings.
%U https://aclanthology.org/2026.acl-long.1180/
%P 25735-25760
Markdown (Informal)
[Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination](https://aclanthology.org/2026.acl-long.1180/) (Cao et al., ACL 2026)
ACL
- Jiawei Cao, Jie Ouyang, Mingyue Cheng, Zhaomeng Zhou, Chunli Liu, Yupeng Li, Zirui Liu, and Shijin Wang. 2026. Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25735–25760, San Diego, California, United States. Association for Computational Linguistics.