@inproceedings{li-etal-2025-alert,
title = "{ALERT}: An {LLM}-powered Benchmark for Automatic Evaluation of Recommendation Explanations",
author = "Li, Yichuan and
Zhang, Xinyang and
Zhang, Chenwei and
Li, Mao and
Liu, Tianyi and
Chen, Pei and
Gao, Yifan and
Lee, Kyumin and
Ding, Kaize and
Wang, Zhengyang and
Zhang, Zhihan and
Shang, Jingbo and
Li, Xian and
Chilimbi, Trishul",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.137/",
doi = "10.18653/v1/2025.naacl-long.137",
pages = "2704--2719",
ISBN = "979-8-89176-189-6",
abstract = "Recommendation explanation systems have become increasingly vital with the widespread adoption of recommender systems. However, existing recommendation explanation evaluation benchmarks suffer from limited item diversity, impractical user profiling requirements, and unreliable and unscalable evaluation protocols. We present ALERT, a model-agnostic recommendation explanation evaluation benchmark. The benchmark comprises three main contributions: 1) a diverse dataset encompassing 15 Amazon e-commerce categories with 2,761 user-item interactions, incorporating implicit preferences through purchase histories;2) two novel LLM-powered automatic evaluators that enable scalable and human-preference aligned evaluation of explanations; and 3) a robust divide-and-aggregate approach that synthesizes multiple LLM judgments, achieving 70{\%} concordance with expert human evaluation and substantially outperforming existing methods.ALERT facilitates comprehensive evaluation of recommendation explanations across diverse domains, advancing the development of more effective explanation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-alert">
<titleInfo>
<title>ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyumin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaize</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trishul</namePart>
<namePart type="family">Chilimbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Recommendation explanation systems have become increasingly vital with the widespread adoption of recommender systems. However, existing recommendation explanation evaluation benchmarks suffer from limited item diversity, impractical user profiling requirements, and unreliable and unscalable evaluation protocols. We present ALERT, a model-agnostic recommendation explanation evaluation benchmark. The benchmark comprises three main contributions: 1) a diverse dataset encompassing 15 Amazon e-commerce categories with 2,761 user-item interactions, incorporating implicit preferences through purchase histories;2) two novel LLM-powered automatic evaluators that enable scalable and human-preference aligned evaluation of explanations; and 3) a robust divide-and-aggregate approach that synthesizes multiple LLM judgments, achieving 70% concordance with expert human evaluation and substantially outperforming existing methods.ALERT facilitates comprehensive evaluation of recommendation explanations across diverse domains, advancing the development of more effective explanation systems.</abstract>
<identifier type="citekey">li-etal-2025-alert</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.137</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.137/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2704</start>
<end>2719</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations
%A Li, Yichuan
%A Zhang, Xinyang
%A Zhang, Chenwei
%A Li, Mao
%A Liu, Tianyi
%A Chen, Pei
%A Gao, Yifan
%A Lee, Kyumin
%A Ding, Kaize
%A Wang, Zhengyang
%A Zhang, Zhihan
%A Shang, Jingbo
%A Li, Xian
%A Chilimbi, Trishul
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F li-etal-2025-alert
%X Recommendation explanation systems have become increasingly vital with the widespread adoption of recommender systems. However, existing recommendation explanation evaluation benchmarks suffer from limited item diversity, impractical user profiling requirements, and unreliable and unscalable evaluation protocols. We present ALERT, a model-agnostic recommendation explanation evaluation benchmark. The benchmark comprises three main contributions: 1) a diverse dataset encompassing 15 Amazon e-commerce categories with 2,761 user-item interactions, incorporating implicit preferences through purchase histories;2) two novel LLM-powered automatic evaluators that enable scalable and human-preference aligned evaluation of explanations; and 3) a robust divide-and-aggregate approach that synthesizes multiple LLM judgments, achieving 70% concordance with expert human evaluation and substantially outperforming existing methods.ALERT facilitates comprehensive evaluation of recommendation explanations across diverse domains, advancing the development of more effective explanation systems.
%R 10.18653/v1/2025.naacl-long.137
%U https://aclanthology.org/2025.naacl-long.137/
%U https://doi.org/10.18653/v1/2025.naacl-long.137
%P 2704-2719
Markdown (Informal)
[ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations](https://aclanthology.org/2025.naacl-long.137/) (Li et al., NAACL 2025)
ACL
- Yichuan Li, Xinyang Zhang, Chenwei Zhang, Mao Li, Tianyi Liu, Pei Chen, Yifan Gao, Kyumin Lee, Kaize Ding, Zhengyang Wang, Zhihan Zhang, Jingbo Shang, Xian Li, and Trishul Chilimbi. 2025. ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2704–2719, Albuquerque, New Mexico. Association for Computational Linguistics.