{"title":"FLARE:融合语言模型和协作架构以增强推荐功能","authors":"Liam Hebert, Marialena Kyriakidi, Hubert Pham, Krishna Sayana, James Pine, Sukhdeep Sodhi, Ambarish Jash","doi":"arxiv-2409.11699","DOIUrl":null,"url":null,"abstract":"Hybrid recommender systems, combining item IDs and textual descriptions,\noffer potential for improved accuracy. However, previous work has largely\nfocused on smaller datasets and model architectures. This paper introduces\nFlare (Fusing Language models and collaborative Architectures for Recommender\nEnhancement), a novel hybrid recommender that integrates a language model (mT5)\nwith a collaborative filtering model (Bert4Rec) using a Perceiver network. This\narchitecture allows Flare to effectively combine collaborative and content\ninformation for enhanced recommendations. We conduct a two-stage evaluation, first assessing Flare's performance\nagainst established baselines on smaller datasets, where it demonstrates\ncompetitive accuracy. Subsequently, we evaluate Flare on a larger, more\nrealistic dataset with a significantly larger item vocabulary, introducing new\nbaselines for this setting. Finally, we showcase Flare's inherent ability to\nsupport critiquing, enabling users to provide feedback and refine\nrecommendations. We further leverage critiquing as an evaluation method to\nassess the model's language understanding and its transferability to the\nrecommendation task.","PeriodicalId":501281,"journal":{"name":"arXiv - CS - Information Retrieval","volume":"43 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement\",\"authors\":\"Liam Hebert, Marialena Kyriakidi, Hubert Pham, Krishna Sayana, James Pine, Sukhdeep Sodhi, Ambarish Jash\",\"doi\":\"arxiv-2409.11699\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Hybrid recommender systems, combining item IDs and textual descriptions,\\noffer potential for improved accuracy. However, previous work has largely\\nfocused on smaller datasets and model architectures. This paper introduces\\nFlare (Fusing Language models and collaborative Architectures for Recommender\\nEnhancement), a novel hybrid recommender that integrates a language model (mT5)\\nwith a collaborative filtering model (Bert4Rec) using a Perceiver network. This\\narchitecture allows Flare to effectively combine collaborative and content\\ninformation for enhanced recommendations. We conduct a two-stage evaluation, first assessing Flare's performance\\nagainst established baselines on smaller datasets, where it demonstrates\\ncompetitive accuracy. Subsequently, we evaluate Flare on a larger, more\\nrealistic dataset with a significantly larger item vocabulary, introducing new\\nbaselines for this setting. Finally, we showcase Flare's inherent ability to\\nsupport critiquing, enabling users to provide feedback and refine\\nrecommendations. We further leverage critiquing as an evaluation method to\\nassess the model's language understanding and its transferability to the\\nrecommendation task.\",\"PeriodicalId\":501281,\"journal\":{\"name\":\"arXiv - CS - Information Retrieval\",\"volume\":\"43 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11699\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11699","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement
Hybrid recommender systems, combining item IDs and textual descriptions,
offer potential for improved accuracy. However, previous work has largely
focused on smaller datasets and model architectures. This paper introduces
Flare (Fusing Language models and collaborative Architectures for Recommender
Enhancement), a novel hybrid recommender that integrates a language model (mT5)
with a collaborative filtering model (Bert4Rec) using a Perceiver network. This
architecture allows Flare to effectively combine collaborative and content
information for enhanced recommendations. We conduct a two-stage evaluation, first assessing Flare's performance
against established baselines on smaller datasets, where it demonstrates
competitive accuracy. Subsequently, we evaluate Flare on a larger, more
realistic dataset with a significantly larger item vocabulary, introducing new
baselines for this setting. Finally, we showcase Flare's inherent ability to
support critiquing, enabling users to provide feedback and refine
recommendations. We further leverage critiquing as an evaluation method to
assess the model's language understanding and its transferability to the
recommendation task.