{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/zero-shot-recommendations-with-pre-trained","title":"Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging","arxiv_id":"2309.01026","date":"2023-09-02","proceeding":null,"authors":["Rachel M. Harrison","Anton Dereventsov","Anton Bibin"],"abstract":"We present a method for zero-shot recommendation of multimodal non-stationary content that leverages recent advancements in the field of generative AI. We propose rendering inputs of different modalities as textual descriptions and to utilize pre-trained LLMs to obtain their numerical representations by computing semantic embeddings. Once unified representations of all content items are obtained, the recommendation can be performed by computing an appropriate similarity metric between them without any additional learning. We demonstrate our approach on a synthetic multimodal nudging environment, where the inputs consist of tabular, textual, and visual data.","url_abs":"https://arxiv.org/abs/2309.01026v2","url_pdf":"https://arxiv.org/pdf/2309.01026v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"zero-shot-recommendations-with-pre-trained","repo_url":"https://github.com/paxnea/llm-multimodal-nudging","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"zero-shot-recommendations-with-pre-trained","repo_url":"https://github.com/paxnea/wain23","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}