Leveraging LLM Reasoning Enhances Personalized Recommender Systems

Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-07
Hauptverfasser: Tsai, Alicia Y, Kraft, Adam, Long, Jin, Cai, Chenwei, Hosseini, Anahita, Xu, Taibai, Zhang, Zemin, Hong, Lichan, Chi, Ed H, Yi, Xinyang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Tsai, Alicia Y
Kraft, Adam
Long, Jin
Cai, Chenwei
Hosseini, Anahita
Xu, Taibai
Zhang, Zemin
Hong, Lichan
Chi, Ed H
Yi, Xinyang
description Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3088983642</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3088983642</sourcerecordid><originalsourceid>FETCH-proquest_journals_30889836423</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRw8kktSy1KTM_MS1fw8fFVCEpNLM7PA_Fc8zIS85JTixUCUouAQok5mVWpKUD55Pzc3NS8lNQiheDK4pLU3GIeBta0xJziVF4ozc2g7OYa4uyhW1CUX1iaWlwSn5VfWgQ0oDje2MDCwtLC2MzEyJg4VQC5CTn6</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3088983642</pqid></control><display><type>article</type><title>Leveraging LLM Reasoning Enhances Personalized Recommender Systems</title><source>Free E- Journals</source><creator>Tsai, Alicia Y ; Kraft, Adam ; Long, Jin ; Cai, Chenwei ; Hosseini, Anahita ; Xu, Taibai ; Zhang, Zemin ; Hong, Lichan ; Chi, Ed H ; Yi, Xinyang</creator><creatorcontrib>Tsai, Alicia Y ; Kraft, Adam ; Long, Jin ; Cai, Chenwei ; Hosseini, Anahita ; Xu, Taibai ; Zhang, Zemin ; Hong, Lichan ; Chi, Ed H ; Yi, Xinyang</creatorcontrib><description>Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Customization ; Large language models ; Reasoning ; Recommender systems</subject><ispartof>arXiv.org, 2024-07</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Tsai, Alicia Y</creatorcontrib><creatorcontrib>Kraft, Adam</creatorcontrib><creatorcontrib>Long, Jin</creatorcontrib><creatorcontrib>Cai, Chenwei</creatorcontrib><creatorcontrib>Hosseini, Anahita</creatorcontrib><creatorcontrib>Xu, Taibai</creatorcontrib><creatorcontrib>Zhang, Zemin</creatorcontrib><creatorcontrib>Hong, Lichan</creatorcontrib><creatorcontrib>Chi, Ed H</creatorcontrib><creatorcontrib>Yi, Xinyang</creatorcontrib><title>Leveraging LLM Reasoning Enhances Personalized Recommender Systems</title><title>arXiv.org</title><description>Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.</description><subject>Customization</subject><subject>Large language models</subject><subject>Reasoning</subject><subject>Recommender systems</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRw8kktSy1KTM_MS1fw8fFVCEpNLM7PA_Fc8zIS85JTixUCUouAQok5mVWpKUD55Pzc3NS8lNQiheDK4pLU3GIeBta0xJziVF4ozc2g7OYa4uyhW1CUX1iaWlwSn5VfWgQ0oDje2MDCwtLC2MzEyJg4VQC5CTn6</recordid><startdate>20240722</startdate><enddate>20240722</enddate><creator>Tsai, Alicia Y</creator><creator>Kraft, Adam</creator><creator>Long, Jin</creator><creator>Cai, Chenwei</creator><creator>Hosseini, Anahita</creator><creator>Xu, Taibai</creator><creator>Zhang, Zemin</creator><creator>Hong, Lichan</creator><creator>Chi, Ed H</creator><creator>Yi, Xinyang</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240722</creationdate><title>Leveraging LLM Reasoning Enhances Personalized Recommender Systems</title><author>Tsai, Alicia Y ; Kraft, Adam ; Long, Jin ; Cai, Chenwei ; Hosseini, Anahita ; Xu, Taibai ; Zhang, Zemin ; Hong, Lichan ; Chi, Ed H ; Yi, Xinyang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30889836423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Customization</topic><topic>Large language models</topic><topic>Reasoning</topic><topic>Recommender systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Tsai, Alicia Y</creatorcontrib><creatorcontrib>Kraft, Adam</creatorcontrib><creatorcontrib>Long, Jin</creatorcontrib><creatorcontrib>Cai, Chenwei</creatorcontrib><creatorcontrib>Hosseini, Anahita</creatorcontrib><creatorcontrib>Xu, Taibai</creatorcontrib><creatorcontrib>Zhang, Zemin</creatorcontrib><creatorcontrib>Hong, Lichan</creatorcontrib><creatorcontrib>Chi, Ed H</creatorcontrib><creatorcontrib>Yi, Xinyang</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tsai, Alicia Y</au><au>Kraft, Adam</au><au>Long, Jin</au><au>Cai, Chenwei</au><au>Hosseini, Anahita</au><au>Xu, Taibai</au><au>Zhang, Zemin</au><au>Hong, Lichan</au><au>Chi, Ed H</au><au>Yi, Xinyang</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Leveraging LLM Reasoning Enhances Personalized Recommender Systems</atitle><jtitle>arXiv.org</jtitle><date>2024-07-22</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_3088983642
source Free E- Journals
subjects Customization
Large language models
Reasoning
Recommender systems
title Leveraging LLM Reasoning Enhances Personalized Recommender Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T20%3A11%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Leveraging%20LLM%20Reasoning%20Enhances%20Personalized%20Recommender%20Systems&rft.jtitle=arXiv.org&rft.au=Tsai,%20Alicia%20Y&rft.date=2024-07-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3088983642%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3088983642&rft_id=info:pmid/&rfr_iscdi=true