@inproceedings{hu-etal-2026-op,
title = "{OP}-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents",
author = "Hu, Yulin and
Long, Zimo and
Guo, Jiahe and
Sui, Xingyu and
Fu, Xing and
Zhao, Weixiang and
Zhao, Yanyan and
Qin, Bing",
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.1168/",
pages = "26770--26827",
ISBN = "979-8-89176-459-0",
abstract = "Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily focus on whether agents can recall and apply user information, while overlooking whether such personalization is used appropriately. In fact, agents may overuse personal information, producing responses that feel forced, intrusive, or socially inappropriate to users. We refer to this issue as **over-personalization**. In this work, we formalize over-personalization into three types: Irrelevance, Repetition, and Sycophancy, and introduce **OP-Bench**, a benchmark of 1,700 verified instances constructed from long-horizon dialogue histories. Using OP-Bench, we evaluate multiple large language models and memory-augmentation methods, and find that over-personalization is widespread when memory is introduced. Further analysis reveals that agents tend to retrieve and over-attend to user memories even when unnecessary. We further evaluate existing post-processing strategies for mitigating this issue, but find that they provide only limited improvements and often reduce personalization performance. Our results highlight over-personalization as a challenging and largely unresolved problem in memory-augmented dialogue systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-op">
<titleInfo>
<title>OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimo</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahe</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyu</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weixiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</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>Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily focus on whether agents can recall and apply user information, while overlooking whether such personalization is used appropriately. In fact, agents may overuse personal information, producing responses that feel forced, intrusive, or socially inappropriate to users. We refer to this issue as **over-personalization**. In this work, we formalize over-personalization into three types: Irrelevance, Repetition, and Sycophancy, and introduce **OP-Bench**, a benchmark of 1,700 verified instances constructed from long-horizon dialogue histories. Using OP-Bench, we evaluate multiple large language models and memory-augmentation methods, and find that over-personalization is widespread when memory is introduced. Further analysis reveals that agents tend to retrieve and over-attend to user memories even when unnecessary. We further evaluate existing post-processing strategies for mitigating this issue, but find that they provide only limited improvements and often reduce personalization performance. Our results highlight over-personalization as a challenging and largely unresolved problem in memory-augmented dialogue systems.</abstract>
<identifier type="citekey">hu-etal-2026-op</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1168/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26770</start>
<end>26827</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
%A Hu, Yulin
%A Long, Zimo
%A Guo, Jiahe
%A Sui, Xingyu
%A Fu, Xing
%A Zhao, Weixiang
%A Zhao, Yanyan
%A Qin, Bing
%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 hu-etal-2026-op
%X Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily focus on whether agents can recall and apply user information, while overlooking whether such personalization is used appropriately. In fact, agents may overuse personal information, producing responses that feel forced, intrusive, or socially inappropriate to users. We refer to this issue as **over-personalization**. In this work, we formalize over-personalization into three types: Irrelevance, Repetition, and Sycophancy, and introduce **OP-Bench**, a benchmark of 1,700 verified instances constructed from long-horizon dialogue histories. Using OP-Bench, we evaluate multiple large language models and memory-augmentation methods, and find that over-personalization is widespread when memory is introduced. Further analysis reveals that agents tend to retrieve and over-attend to user memories even when unnecessary. We further evaluate existing post-processing strategies for mitigating this issue, but find that they provide only limited improvements and often reduce personalization performance. Our results highlight over-personalization as a challenging and largely unresolved problem in memory-augmented dialogue systems.
%U https://aclanthology.org/2026.emnlp-main.1168/
%P 26770-26827
Markdown (Informal)
[OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents](https://aclanthology.org/2026.emnlp-main.1168/) (Hu et al., EMNLP 2026)
ACL
- Yulin Hu, Zimo Long, Jiahe Guo, Xingyu Sui, Xing Fu, Weixiang Zhao, Yanyan Zhao, and Bing Qin. 2026. OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 26770–26827, Budapest, Hungary. Association for Computational Linguistics.