Personalized Language Models

Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data. It remains unclear how well current personalization systems work for real users. In this paper, we study the gap in LLM personalization performance when using synthetic versus human data. We collect human conversations (550 conversations) and judgments across three stages of personalization: extracting user attributes from conversations (5,949 judgments), pairing relevant attributes with new prompts (11,919), and incorporating relevant attributes into a personalized response (1,101). Incorporating human data reveals system limitations at each stage. Models struggle to extract attributes from human conversations, disagree with human judgments on relevant attributes, and generate personalized responses that humans judge no better than generic responses (though that LLM judges widely rate as better). We introduce two lightweight training-based interventions that shift automated personalization evaluation closer to human data in our first two stages. However, in our third stage we find that learned reward models achieve only modest correlation with human ratings, suggesting that human-aligned personalization quality judgments are difficult to model directly. Our collected data provides a foundation for studying how models should extract, select, and incorporate user information in ways that humans find useful.

Personalizing large language models (LLMs) has become a central challenge as LLMs are deployed across recommendation, search, dialogue, and content generation -- settings where the same query should yield different answers given different users. A promising route is to summarize each user's interaction history into a natural-language memory or profile and prepend it to the prompt to facilitate personalization. Existing methods learn such profile generators with explicit rewards derived from labeled downstream tasks, which are expensive and sparse as they require annotated supervision for every target task. In light of this challenge, we introduce Bidirectional User Modeling via Profiles (BUMP), a self-supervised framework that trains a profile generator without any downstream labels. Specifically, given a user's interaction history, we use GRPO to train an LLM to emit a free-form textual profile under a bidirectional in-batch ranking objective: a small LLM judge measures (i) how well the generated profile, used as a query, ranks the user's own held-out interactions above interactions from other users in the batch, and (ii) how well a held-out interaction, used as a query, ranks the user's own profile above profiles of other users. Both directions are scored with multi-positive NDCG and combined into a dense reward per rollout; other users in the batch supply free negatives, so every training example yields supervision from raw interaction logs alone. Evaluated on the LaMP benchmark, BUMP matches or outperforms closed-source APIs and prior methods relying on labeled rewards, while requiring no task label at training.

Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state on top of strong shared foundation models. In this framing, the base model provides shared competence while adapters carry instance-specific behavior such as preferences, skills, tool habits, and memory-like updates. We organize the problem around three scaling axes: Scale Up, where stronger shared priors make small local updates more useful; Scale Down, where we study how small adapters can be while remaining reliable; and Scale Out, where many persistent adapted instances coexist. MinT provides one infrastructure example for managing adapter identity, revision, provenance, evaluation, and serving residency. Together, the results suggest that PEFT can be a compact substrate for persistent personal models rather than only a budget substitute for full fine-tuning.

While LLMs enable personalized chatbots, their effectiveness in child-centered personalization remains unclear, as systematic evaluation of child-specific preferences is still lacking. To address this gap, we introduce ChildEval, a benchmark for evaluating LLMs' ability to infer and follow child-centered preferences in long-context conversations. ChildEval contains 29K synthesized persona profiles of children aged 3-6, providing relatively static background information. Each persona is associated with a child preference-which may align with, conflict with, or be independent of the persona-expressed either explicitly in a single sentence or implicitly through 6-10 turn dialogues. Explicit and implicit preferences are designed to reflect the same underlying preference but differ in expression, capturing dynamic aspects of preference expression rather than changes in the static persona. The benchmark spans five top-level and fourteen sub-level categories covering children's daily lives and development. We further propose fine-grained, child-centric evaluation protocols to systematically assess open-source LLMs. Experimental results demonstrate how different personalized representations affect LLM responses and suggest that finetuning on ChildEval can enhance child-centered performance. Our code and dataset are available at https://github.com/ziyanluo/ChildEval.

Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization methods typically retrieve or summarize user histories in text, or compress them into static latent profiles and soft prompts. These approaches are efficient, but they treat a user's past behavior as an aggregate profile and therefore mix stable identity, recent drift, and item content in the same representation. We propose LAtent Trajectory Tracking and Extrapolation (LATTE), a framework that represents personalization as forecasting a peer anchored relative preference state. For each historical session, LATTE subtracts a time masked baseline formed from comparable users who responded to the same item, producing a state that measures how the target user differs from peers under a shared item context. A lightweight sequence predictor then forecasts the next state in this trajectory, and a State to Token Bridge injects the forecast into a frozen instruction tuned LLM through a single anchored soft token. We provide a latent factor analysis showing when peer anchoring cancels shared item variation and why temporal forecasting trades off stale averages against noisy recent states. Experiments on Amazon Reviews 2023 and MemoryCD show that LATTE consistently outperforms retrieval, summary memory, static latent profiles, difference aware latent profiles, and soft prompt compression baselines. On Amazon Reviews 2023, LATTE improves average ROUGE-L from 0.219 for a static latent profile and 0.245 for the strongest added latent compression baseline to 0.259. Additional pairwise comparisons and diagnostic analyses suggest that the improvement is mainly due to forecasting user-specific trajectory information, rather than merely adding a soft prompt interface.

Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that they do not explicitly state in their prompts. Evaluating whether personalization methods can adapt to these implicit preferences is challenging, since users typically provide prompts rather than reference responses, style preferences are not factually verifiable, and reference-free LLM judges may conflate personalization with general response quality. To address these challenges, we introduce the Arbitrary Preference Mapping (APM) benchmark, which decouples user attributes (e.g. enthusiastic) from response principles (e.g. persuasive) via a hidden, randomized mapping $\mathbf{C}$ that maps user attributes to preferences about response traits. Because $\mathbf{C}$ carries no semantic content and is resampled across runs, models cannot exploit stereotypical associations and must infer preferences from conversation history. Using this unbiased evaluation methodology, we adapt retrieval-augmented, prompt-optimization, and routing personalization methods and evaluate them on Llama-3.1-8B and Qwen-3.5-27B. Our results show that routing is the most reliable approach, while RAG only improves with the stronger base LLM, and soft prompt optimization fails to improve significantly over a non-personalized baseline. Our extensive evaluation reveals that in this realistic setting, personalization remains challenging, but our adapted methods show promise.

Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard constraints, drops rare witnesses, forgets downstream obligations, or answers despite infeasibility. We introduce Contract-Bounded Evidence Activation (CBEA) with Lexicographic Commitment Validation (LCV). CBEA activates a bounded evidence set using typed coverage, tail witnesses, and consequence debt; LCV validates structured commitments before prose and routes infeasible states to repair, abstention, or recontract. Across 360 fixtures and three generation backends, CBEA+LCV reaches zero failures within validator scope at 0.49-0.60 availability over attempted runs. Raw and long-context baselines with the same LCV gate reach zero only at 0.003-0.092. A shadow oracle diagnostic marks the limit: CBEA+LCV recalls 0.012 of uncompiled visible facts, while raw recalls 0.53. The result is a bounded operating point: explicit commitment control and 74-75% lower median input payload, not universal memory dominance.

Current language model systems remain fundamentally stateless across sessions, limiting their ability to personalize interactions over time. While retrieval-augmented generation and fine-tuning improve knowledge access and domain capability, they do not enable persistent understanding of individual users. We propose an emotion-attended stateful memory architecture that dynamically constructs user-specific conversational context using long-term history, emotional signals, and inferred intent at inference time. To evaluate its impact, we conducted a controlled A/B study across thirty non-scripted conversations spanning six emotionally distinct categories using the same underlying language model in both conditions. The memory-enriched condition consistently outperformed the stateless baseline across all evaluated scenarios. The largest gains were observed in memory grounding (95% improvement), plan clarity (57%), and emotional validation (34%). Results remained consistent even in emotionally adversarial conversations involving grief, distress, and uncertainty. These findings suggest that stateful emotional memory may represent a foundational infrastructure layer for hyper-personalized AI systems, though broader validation across larger and more diverse evaluations remains necessary

Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However, fine-tuning models to address all possible combinations of user preferences is computationally expensive and impractical. In this paper, we introduce \textbf{CLIPer}(\textbf{Cl}assifier-guided \textbf{I}nference-time \textbf{Per}sonalization), a lightweight personalization approach that leverages a classifier model to steer LLM generation dynamically to different user preferences at inference time. Our method eliminates the need for extensive fine-tuning, inducing negligible additional computational overhead while enabling more controllable and nuanced personalization across single and multi-dimensional preferences. Comprehensive empirical analyses demonstrate the scalability and effectiveness of our approach in delivering personalized language generation.

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic interpretability perspective and hypothesize the existence of a sparse set of Preference Heads, attention heads that encode user specific stylistic and topical preferences and exert a causal influence on generation. We introduce Differential Preference Steering (DPS), a training free framework that (1) identifies Preference Heads through causal masking analysis and (2) leverages them for controllable and interpretable personalization at inference time. DPS computes a Preference Contribution Score (PCS) for each attention head, directly measuring its causal impact on user aligned outputs. During decoding, we contrast model predictions with and without Preference Heads, amplifying the difference between personalized and generic logits to selectively strengthen preference aligned continuations. Experiments on widely used personalization benchmarks across multiple LLMs demonstrate consistent gains in personalization fidelity while preserving content coherence and low computational overhead. Beyond empirical improvements, DPS provides a mechanistic explanation of where and how personalization emerges within transformer architectures. Our implementation is publicly available.

Despite significant advances in large language models, personalizing them for individual decision-makers remains an open problem. Here, we introduce a synthetic-organic supervision pipeline that transforms raw judicial decisions into instruction-tuning data, enabling parameter-efficient fine-tuning of personalized models for individual judges in low-resource settings. We compare our approach to state-of-the-art personalization techniques across three different tasks and settings. The results show that Causal Language Modeling followed by synthetically generated instruction-tuning significantly outperforms all other baselines, providing significant improvements across lexical, stylistic, and semantic similarity. Notably, our model-generated outputs are indistinguishable from the reasoning of human judges, highlighting the viability of efficient personalization, even in low-resource settings.

Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood. We study activation-based persona vectors representing seven character traits in short-answer generation and automated scoring on the ASAP-SAS benchmark, across three language models spanning dense and mixture-of-experts architectures. Persona steering lowers answer quality overall, with much larger effects on open-ended English Language Arts (ELA) prompts than on factual science prompts. Interpretive and argumentative tasks are particularly sensitive, showing up to 11$\times$ larger degradation. On the scoring side, we observe predictable valence-aligned calibration shifts: evil'' and impolite'' scorers grade more harshly, while good'' and optimistic'' scorers grade more leniently. ELA tasks are 2.5-3$\times$ more susceptible to scorer personalization than science tasks, and the mixture-of-experts model shows roughly 6$\times$ larger calibration shifts than the dense models. To our knowledge, this is the first study to systematically examine the effects of activation-steered persona traits in educational generation and scoring. Our findings highlight the need for task- and architecture-aware calibration when deploying personalized models in educational settings.

Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user preferences. To address this challenge, we propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style. PsPLUG also allows us to tune personalization strength at inference time. Our experiments show that explicit style instructions can diminish personalization in existing methods, whereas PsPLUG better preserves user preferences while providing precise control over the balance between personalization and style adherence.

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that distills heterogeneous user signals into a concise preference summary, and a shared generator that conditions on this summary to produce personalized responses. Both components are trained under a unified preference-optimization objective, with reinforcement learning handling the non-differentiable inference step. This objective decomposes into generator approximation error and summary informativeness, revealing how a single loss simultaneously drives accurate generation and informative summarization. Because the interface is natural language, learned summaries can be inferred once per user and reused across different generators -- including frozen, black-box commercial APIs. Across four personalization benchmarks, POPI generally improves personalization quality while reducing context overhead by up to an order of magnitude.

LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has gained increasing attention as a way to bridge this gap. In this work, we specifically focus on a practical yet challenging setting where only a small set of preference annotations can be collected per user -- a problem we define as Personalized Preference Alignment with Limited Data (PPALLI). To support research in this area, we introduce two datasets -- DnD and ELIP -- and benchmark a variety of alignment techniques on them. We further propose FaST, a highly parameter-efficient approach that leverages high-level features automatically discovered from the data, achieving the best overall performance.