@inproceedings{lu-etal-2024-aligning,
title = "Aligning Large Language Models for Controllable Recommendations",
author = "Lu, Wensheng and
Lian, Jianxun and
Zhang, Wei and
Li, Guanghua and
Zhou, Mingyang and
Liao, Hao and
Xie, Xing",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.443",
doi = "10.18653/v1/2024.acl-long.443",
pages = "8159--8172",
abstract = "Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems {---} systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template, often overlooking the diversity of recommendation tasks and the ability of LLMs to follow recommendation-specific instructions. To address this gap, we first introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs{'} proficiency in adhering to recommendation-specific instructions. Next, we propose a reinforcement learning-based alignment procedure to enhance LLMs{'} generalization ability. Extensive experiments on two real-world datasets demonstrate that our approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2024-aligning">
<titleInfo>
<title>Aligning Large Language Models for Controllable Recommendations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wensheng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxun</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanghua</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems — systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template, often overlooking the diversity of recommendation tasks and the ability of LLMs to follow recommendation-specific instructions. To address this gap, we first introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs’ proficiency in adhering to recommendation-specific instructions. Next, we propose a reinforcement learning-based alignment procedure to enhance LLMs’ generalization ability. Extensive experiments on two real-world datasets demonstrate that our approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.</abstract>
<identifier type="citekey">lu-etal-2024-aligning</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.443</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.443</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8159</start>
<end>8172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Large Language Models for Controllable Recommendations
%A Lu, Wensheng
%A Lian, Jianxun
%A Zhang, Wei
%A Li, Guanghua
%A Zhou, Mingyang
%A Liao, Hao
%A Xie, Xing
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lu-etal-2024-aligning
%X Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems — systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template, often overlooking the diversity of recommendation tasks and the ability of LLMs to follow recommendation-specific instructions. To address this gap, we first introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs’ proficiency in adhering to recommendation-specific instructions. Next, we propose a reinforcement learning-based alignment procedure to enhance LLMs’ generalization ability. Extensive experiments on two real-world datasets demonstrate that our approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.
%R 10.18653/v1/2024.acl-long.443
%U https://aclanthology.org/2024.acl-long.443
%U https://doi.org/10.18653/v1/2024.acl-long.443
%P 8159-8172
Markdown (Informal)
[Aligning Large Language Models for Controllable Recommendations](https://aclanthology.org/2024.acl-long.443) (Lu et al., ACL 2024)
ACL
- Wensheng Lu, Jianxun Lian, Wei Zhang, Guanghua Li, Mingyang Zhou, Hao Liao, and Xing Xie. 2024. Aligning Large Language Models for Controllable Recommendations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8159–8172, Bangkok, Thailand. Association for Computational Linguistics.