{"ID":2849551,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01891","arxiv_id":"2511.01891","title":"Multi-Personality Generation of LLMs at Decoding-time","abstract":"Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibility and robustness. In this paper, we propose a novel Multi-Personality Generation (MPG) framework under the decoding-time combination paradigm. It flexibly controls multi-personality without relying on scarce multi-dimensional models or extra training, leveraging implicit density ratios in single-dimensional models as a \"free lunch\" to reformulate the task as sampling from a target strategy aggregating these ratios. To implement MPG efficiently, we design Speculative Chunk-level based Rejection sampling (SCR), which generates responses in chunks and parallelly validates them via estimated thresholds within a sliding window. This significantly reduces computational overhead while maintaining high-quality generation. Experiments on MBTI personality and Role-Playing demonstrate the effectiveness of MPG, showing improvements up to 16%-18%. Code and data are available at https://github.com/Libra117/MPG .","short_abstract":"Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibility and robustness. I...","url_abs":"https://arxiv.org/abs/2511.01891","url_pdf":"https://arxiv.org/pdf/2511.01891v4","authors":"[\"Rongxin Chen\",\"Yunfan Li\",\"Yige Yuan\",\"Bingbing Xu\",\"Huawei Shen\"]","published":"2025-10-27T09:45:11Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":607717,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2849551,"paper_url":"https://arxiv.org/abs/2511.01891","paper_title":"Multi-Personality Generation of LLMs at Decoding-time","repo_url":"https://github.com/Libra117/MPG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}