{"ID":2855740,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12461","arxiv_id":"2510.12461","title":"Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance","abstract":"In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \\textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, instead of learning ID-based embeddings as in traditional methods. By combining language semantics with graph message passing, this architecture achieves state-of-the-art zero-shot performance, significantly outperforming prior approaches. Furthermore, we introduce \\textbf{TextGCN-MLP}, which extends TextGCN with a trainable multilayer perceptron trained using a contrastive loss, achieving state-of-the-art in-domain performance on recommendation benchmarks. However, the zero-shot performance of TextGCN-MLP remains lower than that of TextGCN, highlighting the trade-off between in-domain specialization and zero-shot generalization. We release our code on github at \\href{https://github.com/ChernovAndrey/TFCE}{github.com/ChernovAndrey/TFCE}.","short_abstract":"In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models....","url_abs":"https://arxiv.org/abs/2510.12461","url_pdf":"https://arxiv.org/pdf/2510.12461v1","authors":"[\"Andrei Chernov\",\"Haroon Wahab\",\"Oleg Novitskij\"]","published":"2025-10-14T12:50:11Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608281,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855740,"paper_url":"https://arxiv.org/abs/2510.12461","paper_title":"Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance","repo_url":"https://github.com/ChernovAndrey/TFCE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}