MIRROR: From Imitation to Internalization in LLM Personalization

Key points

• The demand for personalized LLMs is shifting from style imitation toward content quality.1
• We investigate whether self-distillation can bridge this gap in existing fine-tuning paradigm.1
• 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.1
• 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.1

Sources (1)

• [1]MIRROR: From Imitation to Internalization in LLM Personalization
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 10:10 AM

  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.

  The demand for personalized LLMs is shifting from style imitation toward content quality.

Extractive summary: sentences quoted from the sources.