[
    {
        "id": "osp-15312",
        "type": "article-journal",
        "title": "MIRROR: From Imitation to Internalization in LLM Personalization",
        "author": [
            {
                "family": "Lai",
                "given": "Huayi"
            },
            {
                "family": "Yang",
                "given": "Jicheng"
            },
            {
                "family": "Yi",
                "given": "Min"
            },
            {
                "family": "Meng",
                "given": "Chong"
            }
        ],
        "URL": "https://omanscience.com/en/articles/mirror-from-imitation-to-internalization-in-llm-personalization",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap in existing fine-tuning paradigm. To address this limitation, we introduce MIRROR(Meta- personalization by Internalizing Reference-Revealed On-policy Reflections), a novel self-distillation framework that shifts LLM personalization from imitation toward preference internalization. First, we replace reference-token imitation with reference-revealed on-policy self-distillation, aligning the model's next-token distributions along its own generation trajectories with those of its reference-conditioned self, thereby internalizing user preferences rather than reproducing reference wording.Second, we introduce MIRROR-F, a focal plug-in that augments on-policy distributional alignment with selective supervision over informative reference tokens, thereby strengthening content generation while preserving user-specific expression. Across three personalized generation benchmarks, two model scales, and complementary reference-based and LLM-based evaluations, MIRROR and MIRROR-F achieve leading overall personalization performance and superior text quality, while exhibiting less catastrophic forgetting than SFT-based baselines on three unseen personalized generation tasks. The gains are consistent across model scales and application scenarios, translating to improved performance in LLM personalization tasks."
    }
]