{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:07:38Z","timestamp":1772813258436,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686547","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,4]]},"abstract":"<jats:p>The advent of Large Language Models (LLMs) has the potential to transform item rankings and recommender systems by leveraging extensive training to provide nuanced and personalized suggestions based on comprehensive contextual information about items. LLMs offer advantages, such as easy updating with new preferences and flexibility, in maintaining current relevance. In this paper, we explore the use of LLMs for item rating prediction and recommendation. The LLMs were tested in their capacities as rating predictors and as ranked recommended list generators. We have chosen four advanced LLMs, Llama 3.1 70B, Qwen 2.5 32B, Mistral 7B, and OpenLLaMA 2.0 13B to be rating generators and item recommenders due to their transformer-based architecture. We also conducted an n-shot experimentation and fine tuning to assess how different amounts of data influenced the LLMs\u2019 rating prediction and ranking recommendation. It is theorized that with more data regarding a user\u2019s specific tastes the model will have more accurate results. Specifically, we evaluated three sample sizes\u20145, 10, and each user\u2019s full rating history\u2014plus fine-tuning, to assess how increased sample information affects accuracy. Experimental results showed that traditional User-Based Collaborative Filtering (UBCF) outperformed LLMs in rating prediction, yielding higher accuracy. However, in generating ranked recommendation lists, LLMs exhibited strong performance, with Llama 3.1 70B achieving superior overall results compared to other LLMs and UBCF.<\/jats:p>","DOI":"10.3233\/faia260019","type":"book-chapter","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:20:50Z","timestamp":1772792450000},"source":"Crossref","is-referenced-by-count":0,"title":["LLMs in the Loop: From Ratings to Ranked Recommendations"],"prefix":"10.3233","author":[{"given":"Ethan","family":"Low","sequence":"first","affiliation":[{"name":"Computer Science Dept., Brigham Young Univ., USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiu-Kai","family":"Ng","sequence":"additional","affiliation":[{"name":"Computer Science Dept., Brigham Young Univ., USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Machine Learning and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA260019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:20:50Z","timestamp":1772792450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA260019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"ISBN":["9781643686547"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia260019","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]}}}