{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T04:19:47Z","timestamp":1773807587334,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"41","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this limitation, we propose the Prompt-level User Migration Adapter (PUMA), a lightweight framework to efficiently migrate personalized prompts across incompatible models. PUMA utilizes a parameter-efficient adapter to bridge the semantic gap, combined with a group-based user selection strategy to significantly reduce training costs. Experiments on three large-scale datasets show our method matches or even surpasses the performance of retraining from scratch, reducing computational cost by up to 98%. The framework demonstrates strong generalization across diverse model architectures and robustness in advanced scenarios like chained and aggregated migrations, offering a practical path for the sustainable evolution of personalized AI by decoupling user assets from the underlying models.<\/jats:p>","DOI":"10.1609\/aaai.v40i41.40805","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:19:09Z","timestamp":1773803949000},"page":"35003-35011","source":"Crossref","is-referenced-by-count":0,"title":["Don\u2019t Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs"],"prefix":"10.1609","volume":"40","author":[{"given":"Ziyi","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Chongming","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haoyan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Weinan","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Huifeng","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Fuli","family":"Feng","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40805\/44766","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40805\/44766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:19:12Z","timestamp":1773803952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40805"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"41","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i41.40805","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}