arXiv:2607. 22603v1 Announce Type: new Abstract: Personalized multimodal large language models (MLLMs) aim to generate user-specific responses, but existing methods mainly rely on profile-level information and overlook diverse user preferences.
Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind.
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
MiCRo is a two‑stage framework that improves personalized preference learning for large language models. It first uses a context‑aware mixture model to capture diverse human preferences from large binary preference datasets, then applies an online routing strategy to dynamically adjust mixture weights based on context, reducing ambiguity. Experiments on multiple datasets show that MiCRo captures diverse preferences and enhances downstream personalization.
The paper introduces ReaLMem, a benchmark built from authentic multi‑year personal visual archives with first‑person annotations, designed to evaluate AI systems on factual recall, persona inference, and predictive personalization. It also proposes ChronoProfiler, a temporal‑weighting module that calculates stability scores for user attributes to resolve preference conflicts and enhance personalized decision making. Experiments with multimodal large language models and memory systems show that predictive personalization remains the hardest task, highlight performance gaps, and demonstrate that temporally informed representations significantly improve personalization.
The paper introduces VIBE‑Bench, a new benchmark designed to test personalized large language models (PLLMs) in a regime where user profile cues and query‑specific preferences do not share the same conceptual space, a situation termed profile‑preference conceptual misalignment (PRCM). VIBE‑Bench contains 3,504 personas, 12,239 dialogues, and a manually verified gold test set, and includes two psychology‑grounded tasks that require cross‑concept preference reasoning beyond surface semantic overlap. Experiments show that existing PLLMs largely depend on shallow semantic correlations and struggle to learn robust cross‑concept mappings, highlighting PRCM as a distinct failure mode for personalization models.
arXiv:2603.04191v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactio...
HyperTrace is a training‑free framework that personalizes large language models by tracing latent user preferences online. It maintains interpretable natural‑language hypotheses about short‑term intent and long‑term preferences, updating them with an SMC‑style reweighting process driven by an LLM‑based surrogate choice model. Experiments on PRISM and PersonaMem‑v2 demonstrate that HyperTrace improves response alignment, preference prediction, and profile consistency compared to strong online baselines.
arXiv:2606. 04284v1 Announce Type: cross Abstract: Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values.
The paper introduces a training‑free method for personalizing vision‑language models by using calibrated residual decoding. It constructs three evidence conditions—positive, counterfactual, and empty profiles—to isolate the true contribution of personalization. Normalized‑entropy calibration adjusts the influence of this residual signal based on its uncertainty, improving identity‑sensitive visual personalization without fine‑tuning.
GroupDPO introduces a memory‑efficient approach to group‑wise direct preference optimization for aligning large language models. By using first‑order linearization with per‑response coefficients, the method decouples samples during backpropagation, dramatically reducing peak memory usage and enabling scalable training with larger groups. Experiments in both offline and online settings show that leveraging multiple responses consistently outperforms single‑pair training, and adding a negative log‑likelihood term on positive responses is essential for performance gains and training stability.
arXiv:2606. 07653v1 Announce Type: cross Abstract: Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models can adapt to real-time preferences for different users.
PACIFIC is a framework that aligns large language model responses with user preferences by leveraging stable Big‑Five personality traits as a latent signal. The authors built a 1,200‑pair dataset covering diverse domains and trait directions, and found that trait‑aligned contexts enable LLMs to achieve near‑ceiling accuracy (up to 99%) in personalized QA. They also introduced a persona‑aware contrastive retriever (PiRAG) that improves label‑free accuracy from 30% to 43% over standard semantic retrieval, highlighting retrieval as the main bottleneck.