Personalized Language Model Alignment

Ask about this topic

Overview

Personalized language model alignment studies how models can infer and follow an individual’s preferences from feedback, conversation history, profiles, or behavior rather than relying only on population-wide preferences. Common approaches include personalized preference optimization such as DPO and reinforcement learning, user-specific adapters, memory and retrieval, and inference-time steering or decoding. Evaluation spans preference prediction and generation, multi-turn personalization, and applied settings such as recommendations, privacy, and cultural or political alignment. A central challenge is balancing faithful personalization with safety, truthfulness, and general capability, especially when user signals are sparse, shifting, or in tension with one another.

Latest papers

CardsList

61 papers12 papers in the last four weeks, up 140% on the four weeks before. 0.1% of all new papers.

Apr 24, 2026

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

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.

Weixu Zhang, Ye Yuan, Changjiang Han +7

McGill University · Mila - Quebec AI Institute · MBZUAI +2

LLM AlignmentLanguage Model SteeringLLM PersonalizationLLM InterpretabilityPersonalized Language ModelsPersonalized Language Model Alignment+1
AskPDF
Apr 14, 2026

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving individual preferences. We present a new dataset, Value Conflict Dilemma (VCD), which includes scenarios that involve conflicting human preferences, facilitating the evaluation of our approach. Our experiments demonstrate that PFT outperforms single-preference training methods, achieving up to 96.6% accuracy in multi-choice classification tasks and the highest open-ended generation score of 8.69. PFT also shows significant improvements over DPO, SFT and some traditional training methods, especially when handling conflicting preferences. Additionally, with limited user history data, models can inferring preference vector rapidly, achieving a 44.76% improvement in user-specific preference alignment in comparison to single-preference models.

Shanyong Wang, Shuhang Lin, Yining Zhao +2

Rutgers University—New Brunswick · University of Illinois at Urbana-Champaign

LLM Fine-TuningPersonalized Language Model AlignmentPreference AlignmentValue AlignmentUser Preference ModelingMulti-Objective Language Model Alignment
AskPDF
Apr 13, 2026

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization

Mobile GUI agents powered by Multimodal Large Language Models (MLLMs) can execute complex tasks on mobile devices. Despite this progress, most existing systems still optimize task success or efficiency, neglecting users' privacy personalization. In this paper, we study the often-overlooked problem of agent personalization. We observe that personalization can induce systematic structural heterogeneity in execution trajectories. For example, privacy-first users often prefer protective actions, e.g., refusing permissions, logging out, and minimizing exposure, leading to logically different execution trajectories from utility-first users. Such variable-length and structurally different trajectories make standard preference optimization unstable and less informative. To address this issue, we propose Trajectory Induced Preference Optimization (TIPO), which uses preference-intensity weighting to emphasize key privacy-related steps and padding gating to suppress alignment noise. Results on our Privacy Preference Dataset show that TIPO improves persona alignment and distinction while preserving strong task executability, achieving 65.60% SR, 46.22 Compliance, and 66.67% PD, outperforming existing optimization methods across various GUI tasks. The code and dataset will be publicly released at https://github.com/Zhixin-L/TIPO.

Zhixin Lin, Jungang Li, Dongliang Xu +5

Shandong University · The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology +4

Mobile GUI AgentsPersonalized Language Model AlignmentPreference OptimizationUser Preference Modeling
AskPDF
Apr 10, 2026

Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation

Large language model (LLM) agents are increasingly deployed as scalable user simulators for recommender system evaluation. Yet existing simulators perceive recommendations through text or structured metadata rather than the visual interfaces real users browse-a critical gap, since attention over recommendation layouts is both visually driven and highly personalized. We investigate whether aligning a vision-language model's (VLM's) visual attention with user-specific gaze patterns can improve simulation fidelity. Analysis of a real-world eye-tracking dataset collected in a carousel-based recommendation setting reveals that users exhibit stable individual gaze patterns strongly predictive of click behavior. Building on this finding, we propose Fixation-Aligned Tuning for user Emulation (FixATE). Our approach first probes the VLM's internal visual attention via interpretability operators to obtain a slot-level relevance distribution comparable with human fixation, and then learns personalized soft prompts to steer the model's attention toward each user's characteristic fixation pattern. Experiments across three interpretability-based probing operators and two architecturally distinct VLM backbones demonstrate consistent improvements in both attention alignment and click prediction accuracy. These results suggest that making the model "see like the user" is a viable path toward simulators that more faithfully reproduce how users perceive and act in recommendation interfaces.

Lingfeng Huang, Huizhong Guo, Tianjun Wei +2

Singapore University of Technology and Design, Singapore · Zhejiang University, Hangzhou, China · Nanyang Technological University, Singapore

User SimulationVLM AdaptationPersonalized Language Model Alignment
AskPDF
Apr 10, 2026

The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs

Telling an LLM to "be enthusiastic" raises its sycophancy rate from 30% to 50% on a lightly-aligned model, but has zero effect on a strongly-aligned one. We define this gap as the alignment floor, Δfloor(m)=max⁡pS(m,p)−min⁡pS(m,p)Δ_{\text{floor}}(m)=\max_pS(m,p)-\min_pS(m,p), the range of sycophancy rates a model produces across persona conditions, and treat sycophancy as a persona-conditional property rather than a fixed model property. Pluralistic AI relies on behavioral adaptation via persona prompts like "be creative" or "be thorough", which let systems respect diverse user values and communication styles; the safety question is how much customization a given model can absorb before its truthfulness shifts. We present a controlled case study contrasting a strongly-aligned RLHF + Constitutional-AI model (Claude Sonnet 4.6) with a more lightly-aligned model (Amazon Nova Lite), spanning seven persona conditions and five tasks for 1800 total runs. An existence-pair result motivates per-model auditing: there is at least one strongly-aligned model with Δfloor=5Δ_{\text{floor}}=5pp (within 5pp of the 15% control rate) and at least one lightly-aligned model with 45pp (5%--50% range). On the lightly-aligned model, all five Big Five personas increase sycophancy over control, and counterintuitively Agreeableness produces the smallest increase, not the largest. The single largest effect in the study is constructive: a Skeptic persona reduces sycophancy by 25pp on the lightly-aligned model, and is the only persona that instructs resistance against user claims rather than engagement with them, suggesting a directionality account. Cross-model transfer of persona effects is near-zero, so persona-alignment testing must be per-model. We propose ΔfloorΔ_{\text{floor}} as a deployment-time audit metric: measure it on a small persona panel before deploying persona customization.

Xing Zhang, Guanghui Wang, Yanwei Cui +4

AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China

Language Model Safety EvaluationPersonalized Language Model AlignmentPersona PromptingLLM Sycophancy
AskPDF
Apr 10, 2026

PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment

Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specific characters. However, identifying an optimal persona is time-consuming, and its impact on output quality remains poorly understood. Prior work has mainly addressed this issue at the prompt level via inference-time strategies, incurring additional computation. In this work, we avoid inference-time prompt search by tackling persona sensitivity during training, aiming to train models that adapt their behavior to diverse personas while preserving task performance. In particular, we find that reinforcement learning with verifiable rewards (RLVR) systematically reduces sensitivity to persona prompts, but also reveals an inherent trade-off of outcome-based optimization: while RLVR improves robustness on tasks with verifiable goals, it can also degrade persona expressivity when needed, e.g., in-character role-playing. To address this limitation, we propose PerMix-RLVR, a persona-mixed RLVR strategy that mitigates the persona robustness-fidelity trade-off, preserving strong robustness to harmful persona variation while enabling faithful persona adoption when required. Concretely, PerMix-RLVR improves persona stability score (PSS) over RLVR by +21.2% on MATH500, while also enhancing persona fidelity by +11.4% on PersonaGym.

Jihwan Oh, Soowon Oh, Murad Aghazada +3

KAIST AI · Samsung Advanced Institute of Technology

Personalized Language Model AlignmentLanguage Model RobustnessReinforcement Learning with Verifiable RewardsPersonality Modeling in Language Models
AskPDF
Apr 6, 2026

One Model for All: Multi-Objective Controllable Language Models

Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from human feedback (RLHF) mainly focuses on a fixed reward learned from average human ratings, which may weaken the adaptability and controllability of varying preferences. However, creating personalized LLMs requires aligning LLMs with individual human preferences, which is non-trivial due to the scarce data per user and the diversity of user preferences in multi-objective trade-offs, varying from emphasizing empathy in certain contexts to demanding efficiency and precision in others. Can we train one LLM to produce personalized outputs across different user preferences on the Pareto front? In this paper, we introduce Multi-Objective Control (MOC), which trains a single LLM to directly generate responses in the preference-defined regions of the Pareto front. Our approach introduces multi-objective optimization (MOO) principles into RLHF to train an LLM as a preference-conditioned policy network. We improve the computational efficiency of MOC by applying MOO at the policy level, enabling us to fine-tune a 7B-parameter model on a single A6000 GPU. Extensive experiments demonstrate the advantages of MOC over baselines in three aspects: (i) controllability of LLM outputs w.r.t. user preferences on the trade-off among multiple rewards; (ii) quality and diversity of LLM outputs, measured by the hyper-volume of multiple solutions achieved; and (iii) generalization to unseen preferences. These results highlight MOC's potential for real-world applications requiring scalable and customizable LLMs.

Qiang He, Yucheng Yang, Tianyi Zhou +3

Ruhr University Bochum · Eindhoven University of Technology · Mohamed bin Zayed University of Artificial Intelligence +1

Multi-Objective Language Model AlignmentControllable Text GenerationPersonalized Language Model AlignmentRL from Human FeedbackMulti-Objective Reinforcement Learning
AskPDF
Apr 5, 2026

High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making

Personalized LLM systems have advanced rapidly, yet most operate in domains where user preferences are stable and ground truth is either absent or subjective. We argue that individual investor decision-making presents a uniquely challenging domain for LLM personalization - one that exposes fundamental limitations in current customization paradigms. Drawing on our system, built and deployed for AI-augmented portfolio management, we identify four axes along which individual investing exposes fundamental limitations in standard LLM customization: (1) behavioral memory complexity, where investor patterns are temporally evolving, self-contradictory, and financially consequential; (2) thesis consistency under drift, where maintaining coherent investment rationale over weeks or months strains stateless and session-bounded architectures; (3) style-signal tension, where the system must simultaneously respect personal investment philosophy and surface objective evidence that may contradict it; and (4) alignment without ground truth, where personalization quality cannot be evaluated against a fixed label set because outcomes are stochastic and delayed. We describe the architectural responses that emerged from building the system and propose open research directions for personalized NLP in high-stakes, temporally extended decision domains.

Yash Ganpat Sawant

Personalized Language ModelsPersonalized Language Model AlignmentUser ModelingFinancial Decision-Making
AskPDF
Apr 5, 2026

Many Preferences, Few Policies: Compact Portfolios for Multi-Objective LLM Alignment

Aligning large language models (LLMs) requires balancing competing objectives such as helpfulness, harmlessness, and conciseness. The appropriate balance varies across users and applications, yet training, evaluating, and deploying many policies across different reward weights is costly. We study how to identify a small portfolio of LLMs that preserves near-optimal performance across all reward weightings. We propose PALM (Portfolio of Aligned LLMs), an algorithm that combines a structured grid of weight vectors, a lazy search that optimizes policies only where needed, and pruning. Given target approximation tolerances, PALM returns a portfolio that provably contains a near-optimal policy for every weight vector, with an explicit upper bound on portfolio size. Such portfolios can support scalable personalization, reward-weight exploration during model development, and compact decoding-time configurations. Experiments show that PALM generally achieves smaller approximation gaps than same-size portfolios built from uniformly spaced or randomly sampled weights. We further demonstrate that PALM scales effectively to higher-dimensional reward spaces through efficient search and sparse preference structure.

Cheol Woo Kim, Jai Moondra, Roozbeh Nahavandi +3

Carnegie Mellon University · Massachusetts Institute of Technology

Multi-Objective Language Model AlignmentPersonalized Language Model AlignmentPareto Optimization
AskPDF
Apr 2, 2026

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation

Multilingual large language models (MLLMs) often answer culturally ambiguous questions inconsistently across languages, even for a fixed user persona -- e.g., Shakespeare in English but Cervantes in Spanish for the same British user. To robustly quantify this Cross-lingual Cultural Inconsistency, we introduce Singleton Fleiss's κSκ_S, a metric mathematically resilient to hallucinations. For mitigation, we propose Cross-lingual Cultural Consistent Preference Optimisation (C-3PO), a consensus-driven alignment framework. C-3PO raises κSκ_S by 0.07--0.10 over unaligned models, above every prompting and representation steering baseline averaged across personas, whilst largely preserving explicit user identities, cultural neutrality and intrinsic cultural knowledge; where it does not, a soft-consensus variant recovers most of the cost. Although trained only on multiple-choice questions, C-3PO also improves consistency in open-ended generation. Empirical evaluations demonstrate this inconsistency is more pronounced for lower-resource languages like Indonesian and Persian. Finally, early decoding of intermediate layers reveals that MLLMs implicitly personalise outputs towards the prompt language's stereotypical culture as forward-pass representations stabilise.

Lucas Resck, Isabelle Augenstein, Anna Korhonen

Language Technology Lab, University of Cambridge · University of Copenhagen

Cross-Lingual Consistency in Language ModelsCross-Cultural Language Model EvaluationPreference OptimizationPersonalized Language Model Alignment
AskPDF
Apr 1, 2026

Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization

Reward factorization personalizes large language models (LLMs) by decomposing rewards into shared basis functions and user-specific weights. Yet, existing methods estimate user weights from scarce data in isolation and as deterministic points, leading to inaccurate and unreliable inference. We introduce Variational Reward Factorization (VRF), an uncertainty-aware framework that represents each user's preferences as a variational distribution in a shared preference space. VRF infers user distributions via a variational encoder, derives weights through Wasserstein distance matching with shared probabilistic bases, and downweights uncertain estimates through a variance-attenuated loss. On three benchmarks, VRF outperforms all baselines across seen and unseen users, few-shot scenarios, and varying uncertainty levels, with gains extending to downstream alignment. Our code is available at https://github.com/Gyu-Seok-Lee/VRF_COLM26.

Gyuseok Lee, Wonbin Kweon, Zhenrui Yue +3

University of Illinois Urbana-Champaign · Korea University

Personalized Language ModelsPersonalized Language Model AlignmentUser Preference ModelingReward Modeling
AskPDF
Apr 1, 2026

Dual Optimal: Make Your LLM Peer-like with Dignity

Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. We propose the Dignified Peer framework, which counters servility with anti-sycophancy and trustworthiness, and mitigates evasiveness through empathy and creativity. Realizing this agent requires overcoming significant challenges in data supervision, objective collapse, and evaluation bias. We address these issues by introducing the PersonaKnob dataset which features a compositional partial order structure of multiple persona preference. This data is utilized alongside a tolerant constrained Lagrangian DPO algorithm that dynamically balances all persona dimensions to prevent behavioral collapse. Additionally, we employ a psychometrically calibrated Item Response Theory evaluation protocol to disentangle latent model persona capability from confounders like judge biases. Extensive empirical studies demonstrate that our approach successfully build a LLM agent with both dignity and peer.

Xiangqi Wang, Yue Huang, Haomin Zhuang +2

Department of Computer Science and Engineering, University of Notre Dame

Personalized Language Model AlignmentPersonality Modeling in Language Models
AskPDF
Mar 30, 2026

EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

Pluralistic alignment is essential for adapting large language models (LLMs) to the diverse preferences of individuals and minority groups. However, existing approaches often mix stable personal traits with episode-specific factors, limiting their ability to generalize across episodes. To address this challenge, we introduce EpiPersona, a framework for explicit persona-episode coupling. EpiPersona first projects noisy preference feedback into a low-dimensional persona space, where similar personas are aggregated into shared discrete codes. This process separates enduring personal characteristics from situational signals without relying on predefined preference dimensions. The inferred persona representation is then coupled with the current episode, enabling episode-aware preference prediction. Extensive experiments show that EpiPersona consistently outperforms the baselines. It achieves notable performance gains in hard episodic-shift scenarios, while remaining effective with sparse preference data.

Yujie Zhang, Weikang Yuan, Zhuoren Jiang +1

Zhejiang University.

User Preference ModelingPersonalized Language Model AlignmentPersonality Modeling in Language Models
AskPDF
Mar 27, 2026

Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles

AI agents that communicate on behalf of individuals need to capture how each person actually communicates, yet current approaches either require costly per-person fine-tuning, produce generic outputs from shallow persona descriptions, or optimize preferences without modeling communication style. We present ASPECT (Automated Social Psychometric Evaluation of Communication Traits), a pipeline that directs LLMs to assess constructs from a validated communication scale against behavioral evidence from workplace data, without per-person training. In a case study with 20 participants (1,840 paired item ratings, 600 scenario evaluations), ASPECT-generated profiles achieved moderate alignment with self-assessments, and ASPECT-generated responses were preferred over generic and self-report baselines on aggregate, with substantial variation across individuals and scenarios. During the profile review phase, linked evidence helped participants identify mischaracterizations, recalibrate their own self-ratings, and negotiate context-appropriate representations. We discuss implications for building inspectable, individually scoped communication profiles that let individuals control how agents represent them at work.

Ruoxi Shang, Dan Marshall, Edward Cutrell +1

University of Washington, Seattle, Washington, USA · Microsoft Research, Redmond, Washington, USA

Personal AI AgentsPersonalized Language Model AlignmentHuman-Centered AILLM Agent Evaluation
AskPDF
Mar 24, 2026

KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao

Large Language Models (LLMs) are equipped with profound semantic knowledge, making them a natural choice for injecting semantic generalization into personalized search systems. However, in practice we find that directly fine-tuning LLMs on industrial personalized tasks (e.g. next item prediction) often yields suboptimal results. We attribute this bottleneck to a critical Knowledge--Action Gap: the inherent conflict between preserving pre-trained semantic knowledge and aligning with specific personalized actions by discriminative objectives. Empirically, action-only training objectives induce Semantic Collapse, such as attention "sinks". This degradation severely cripples the LLM's generalization, failing to bring improvements to personalized search systems. We propose KARMA (Knowledge--Action Regularized Multimodal Alignment), a unified framework that treats semantic reconstruction as a train-only regularizer. KARMA optimizes a next-interest embedding for retrieval (Action) while enforcing semantic decodability (Knowledge) through two complementary objectives: (i) history-conditioned semantic generation, which anchors optimization to the LLM's native next-token distribution, and (ii) embedding-conditioned semantic reconstruction, which constrains the interest embedding to remain semantically recoverable. On Taobao search system, KARMA mitigates semantic collapse (attention-sink analysis) and improves both action metrics and semantic fidelity. In ablations, semantic decodability yields up to +22.5 HR@200. With KARMA, we achieve +0.25 CTR AUC in ranking, +1.86 HR in pre-ranking and +2.51 HR in recalling. Deployed online with low inference overhead at ranking & pre-ranking stage, KARMA drives +0.9% increase in GMV.

Zhi Sun, Wenming Zhang, Yi Wei +4

Taobao & Tmall Group of Alibaba, Hangzhou, China

Information RetrievalPersonalized Language Model AlignmentLarge Language Model-Based Recommendation
AskPDF
Mar 20, 2026

FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment

Aligning large language models (LLMs) with human preferences in federated learning (FL) is challenging due to decentralized, privacy-sensitive, and highly non-IID preference data. Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning with human feedback (RLHF), but its direct application in FL suffers from severe performance degradation under non-IID data and limited generalization of implicit rewards. To bridge this gap, we propose FedPDPO (Federated Personalized Direct Preference Optimization), a personalized federated framework for preference alignment of LLMs. It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation. To address non-IID heterogeneity, we devise (1) the globally shared LoRA adapter with the personalized client-specific LLM head. Moreover, we introduce (2) a personalized DPO training strategy with a client-specific explicit reward head to complement implicit rewards and further alleviate non-IID heterogeneity, and (3) a bottleneck adapter to balance global and local features. We provide theoretical analysis establishing the probabilistic foundation and soundness. Extensive experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.

Kewen Zhu, Liping Yi, Zhiming Zhao +3

College of Intelligence and Computing, Tianjin University, Tianjin, China · College of Computing and Data Science, Nanyang Technological University, Singapore

Personalized Language Model AlignmentDirect Preference OptimizationFederated Fine-TuningNon-IID Federated Learning
AskPDF
Mar 19, 2026

Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM

Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial and human-centered tasks require high-level human alignment. Prior works provide mixed opinions on their utility: some report performance gains when using expert personas for certain domains and their contribution to data diversity in synthetic data creation, while others find near-zero or negative impact on general utility. To fully leverage the benefits of the LLM persona and avoid its harmfulness, a more comprehensive investigation of the mechanism is crucial. In this work, we study how model optimization, task type, prompt length, and placement can impact expert persona effectiveness across instruction-tuned and reasoning LLMs, and provide insight into conditions under which expert personas fail and succeed. Based on our findings, we developed a pipeline to fully leverage the benefits of an expert persona, named PRISM (Persona Routing via Intent-based Self-Modeling), which self-distills an intent-conditioned expert persona into a gated LoRA adapter through a bootstrapping process that requires no external data, models, or knowledge. PRISM enhances human preference and safety alignment on generative tasks while maintaining accuracy on discriminative tasks across all models, with minimal memory and computing overhead.

Zizhao Hu, Mohammad Rostami, Jesse Thomason

University of Southern California Los Angeles, California, USA

Persona-Conditioned GenerationPersonalized Language Model AlignmentLLM Safety Alignment
AskPDF
Mar 13, 2026

Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits personalization. Variational Preference Learning (VPL) seeks to address this by introducing user-specific latent variables. Despite its promise, we found that VPL suffers from posterior collapse. While this phenomenon is well known in VAEs, it has not previously been identified in preference learning frameworks. Under sparse preference data and with overly expressive decoders, VPL may cause latent variables to be ignored, reverting to a single-reward model. To overcome this limitation, we propose Swap-guided Preference Learning (SPL). The key idea is to construct fictitious swap annotators and use the mirroring property of their preferences to guide the encoder. SPL introduces three components: (1) swap-guided base regularization, (2) Preferential Inverse Autoregressive Flow (P-IAF), and (3) adaptive latent conditioning. Experiments show that SPL mitigates collapse, enriches user-specific latents, and improves preference prediction. Our code and data are available at https://github.com/cobang0111/SPL

Gihoon Kim, Euntai Kim

Yonsei University · Korea Institute of Science and Technology

Preference LearningRL from Human FeedbackPersonalized Language Model AlignmentUser Preference ModelingPosterior Collapse
AskPDF
Mar 11, 2026

Aligning Large Language Models with Searcher Preferences

The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and deployment of open-ended generative search on large content platforms remain limited. This setting introduces challenges, including robustness to noisy retrieval, non-negotiable safety guarantees, and alignment with diverse user needs. In this work, we introduce SearchLLM, the first large language model (LLM) for open-ended generative search. We design a hierarchical, multi-dimensional reward system that separates bottom-line constraints, including factual grounding, basic answer quality and format compliance, from behavior optimization objectives that promote robustness to noisy retrieval and alignment with user needs. Concretely, our reward model evaluates responses conditioned on the user query, session history, and retrieved evidence set, combining rule-based checks with human-calibrated LLM judges to produce an interpretable score vector over these dimensions. We introduce a Gated Aggregation Strategy to derive the training reward for optimizing SearchLLM with Group Relative Policy Optimization (GRPO). We deploy SearchLLM in the AI search entry of RedNote. Offline evaluations and online A/B tests show improved generation quality and user engagement, increasing Valid Consumption Rate by 1.03% and reducing Re-search Rate by 2.81%, while upholding strict safety and reliability standards.

Wei Wu, Peilun Zhou, Liyi Chen +6

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China · Xiaohongshu Inc., Beijing, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1

Personalized Language Model AlignmentGenerative Retrieval
AskPDF
Mar 9, 2026

AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment

As Large Language Models (LLMs) evolve into lifelong AI assistants, LLM personalization has become a critical frontier. However, progress is currently bottlenecked by the absence of a gold-standard evaluation benchmark. Existing benchmarks either overlook personalized information management that is critical for personalization or rely heavily on synthetic dialogues, which exhibit an inherent distribution gap from real-world dialogue. To bridge this gap, we introduce AlpsBench, An LLM PerSonalization benchmark derived from real-world human-LLM dialogues. AlpsBench comprises 2,500 long-term interaction sequences curated from WildChat, paired with human-verified structured memories that encapsulate both explicit and implicit personalization signals. We define four pivotal tasks - personalized information extraction, updating, retrieval, and utilization - and establish protocols to evaluate the entire lifecycle of memory management. Our benchmarking of frontier LLMs and memory-centric systems reveals that: (i) models struggle to reliably extract latent user traits; (ii) memory updating faces a performance ceiling even in the strongest models; (iii) retrieval accuracy declines sharply in the presence of large distractor pools; and (iv) while explicit memory mechanisms improve recall, they do not inherently guarantee more preference-aligned or emotionally resonant responses. AlpsBench aims to provide a comprehensive framework.

Jianfei Xiao, Xiang Yu, Chengbing Wang +8

University of Science and Technology of China · National University of Singapore

LLM PersonalizationPersonalized Language Model AlignmentPersistent Memory for Language ModelsLLM Evaluation
AskPDF
Mar 5, 2026

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment

Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handle only coarse-grained attributes. In practice, fine-tuning LLMs on task-specific datasets to optimize value alignment inevitably incurs an alignment tax: the model's pre-calibrated value system drifts significantly due to latent bias absorption from training data, while the fine-tuning process also causes severe hallucinations and semantic information loss in generated responses. To address this, we propose VISA (Value Injection via Shielded Adaptation), a closed-loop framework designed to navigate this trade-off. VISA's architecture features a high-precision value detector, a semantic-to-value translator, and a core value-rewriter. The value-rewriter is trained via Group Relative Policy Optimization (GRPO) with a composite reward function that simultaneously optimizes for fine-grained value precision, and the preservation of semantic integrity. By learning an optimal policy to balance these competing objectives, VISA effectively mitigates the alignment tax while staying loyal to the original knowledge. Our experiments demonstrate that this approach enables precise control over a model's value expression while maintaining its factual consistency and general capabilities, significantly outperforming both standard fine-tuning methods and prompting-based baselines, including GPT-4o.

Jiawei Chen, Tianzhuo Yang, Guoxi Zhang +3

Peking University, Beijing, China

LLM AlignmentPersonalized Language Model AlignmentMulti-Objective Language Model Alignment
AskPDF
Mar 3, 2026

SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems

Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which recommendation outputs may negatively impact users by violating personalized safety constraints, when individualized safety sensitivities -- such as trauma triggers, self-harm history, or phobias -- are implicitly inferred from the conversation but not respected during recommendation. We formalize this challenge as personalized CRS safety and introduce SafeRec, a new benchmark dataset designed to systematically evaluate safety risks in LLM-based CRS under user-specific constraints. To further address this problem, we propose SafeCRS, a safety-aware training framework that integrates Safe Supervised Fine-Tuning (Safe-SFT) with Safe Group reward-Decoupled Normalization Policy Optimization (Safe-GDPO) to jointly optimize recommendation quality and personalized safety alignment. Extensive experiments on SafeRec demonstrate that SafeCRS reduces safety violation rates by up to 96.5% relative to the strongest recommendation-quality baseline while maintaining competitive recommendation quality. Warning: This paper contains potentially harmful and offensive content.

Haochang Hao, Yifan Xu, Xinzhuo Li +2

University of Illinois at Chicago Chicago, IL, USA · University of Notre Dame South Bend, IN, USA · Amazon Santa Clara, CA, USA

Recommender SystemsLarge Language Model-Based RecommendationLLM Safety AlignmentPersonalized Language Model Alignment
AskPDF
Mar 2, 2026

Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents

The utility of Role-Playing Language Agents in sociological research is growing alongside the adoption of Large Language Models. For realism in social simulation, these agents must adhere to their personas defined by character profiles, yet existing strategies-static prompt engineering or costly fine-tuning-fail to adapt personas to dynamic scenarios. Psychological theories, such as the Cognitive-Affective Personality Systems, provide a crucial explanation for this failure: a persona's influence on behavior is not static but varies with the scenarios. This context-dependence highlights the critical need for adaptive persona management. To address this gap, we propose a novel, theory-driven method that dynamically estimates context-dependent persona importance and integrates it into weighted reward-guided decoding, enabling inference-time persona following. Specifically, we introduce the Persona Dynamic Decoding (PDD) framework, which consists of two key components: (1) Persona Importance Estimation (PIE) module, which dynamically quantifies the contextual importance of persona attributes without requiring ground-truth supervision; and (2) Persona-Guided Inference-Time Alignment (PIA) paradigm, which leverages these importance scores to construct weighted multi-objective rewards and modulate generation probabilities during inference. Extensive experiments show the effectiveness of our method in utterance consistency and behavioral fidelity.

Yuxin Liu, Mingye Zhu, Siyuan Liu +2

University of Science and Technology of China

Large Language Model-Based Role-Play SimulationPersona-Conditioned GenerationInference-Time Language Model AlignmentPersonalized Language Model AlignmentLanguage Model Decoding
AskPDF
Mar 1, 2026

Reasoning Boosts Opinion Alignment in LLMs

Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital democracies, where models could help shape fairer and more popular policies. Given their versatility, strong generalization capabilities, and demonstrated success across diverse text-to-text applications, large language models (LLMs) are natural candidates for this task. However, due to their statistical nature and limited causal understanding, they tend to produce biased opinions when prompted naively. In this work, we study whether reasoning can improve opinion alignment. Motivated by the recent advancement in mathematical reasoning enabled by reinforcement learning (RL), we train models to produce profile-consistent answers through structured reasoning. We evaluate our approach on three datasets covering U.S., European, and Swiss politics. Results indicate that reasoning enhances opinion modeling and is competitive with strong baselines, but does not fully remove bias, highlighting the need for additional mechanisms to build faithful political digital twins using LLMs. By releasing both our method and datasets, we establish a solid baseline to support future research on LLM opinion alignment.

Frédéric Berdoz, Yann Billeter, Yann Vonlanthen +1

ETH Zurich, Switzerland

Political Bias in Language ModelsPersonalized Language Model Alignment
AskPDF
Feb 22, 2026

Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering

Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-augmented generation (RAG) solutions that construct personal context by retrieving relevant items from the user's profile. Existing methods use the user's query directly to retrieve personal documents, and such strategies often lead to surface-level personalization. We propose PR2 (Personalized Retrieval-Augmented Reasoning), a reinforcement learning framework that integrates reasoning and retrieval from personal context for personalization. PR2 learns adaptive retrieval-reasoning policies, determining when to retrieve, what evidence to retrieve from user profiles, and how to incorporate it into intermediate reasoning steps. By optimizing multi-turn reasoning trajectories under a personalized reward function, the framework reinforces reasoning paths that better align with user-specific preferences and contextual signals reflected by the reward model. Extensive experiments on the LaMP-QA benchmark using three LLMs show that PR2 consistently outperforms strong baselines, achieving an average relative improvement of 8.8%-12% in personalized QA.

Maryam Amirizaniani, Alireza Salemi, Hamed Zamani

University of Washington Seattle, WA, USA · University of Massachusetts Amherst Amherst, MA, USA

Question AnsweringRetrieval-Augmented GenerationAgentic RAGRL for Language Model ReasoningPersonalized Language Model Alignment
AskPDF
Feb 18, 2026

Aligning Language Models from User Interactions

Multi-turn user interactions are among the most abundant data produced by language models, yet we lack effective methods to learn from them. While typically discarded, these interactions often contain useful information: follow-up user messages may indicate that a response was incorrect, failed to follow an instruction, or did not align with the user's preferences. Importantly, language models are already able to make use of this information in context. After observing a user's follow-up, the same model is often able to revise its behavior. We leverage this ability to propose a principled and scalable method for learning directly from user interactions through self-distillation. By conditioning the model on the user's follow-up message and comparing the resulting token distribution with the original policy, we obtain a target for updating the policy that captures how the model's behavior changes in hindsight. We then distill this hindsight distribution back into the current policy. Remarkably, we show that training on real-world user conversations from WildChat improves language models across standard alignment and instruction-following benchmarks, without regressing other capabilities. The same mechanism enables personalization, allowing models to continually adapt to individual users through interaction without explicit feedback. Our results demonstrate that raw user interactions that arise naturally during deployment enable alignment, personalization, and continual adaptation.

Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor +3

ETH Zurich · MIT · University of Zurich

LLM AlignmentPersonalized Language Model AlignmentSelf-Training for Language ModelsContinual Learning for LLMsLanguage Model Distillation
AskPDF
Feb 17, 2026

Multi-Objective Alignment of Language Models for Personalized Psychotherapy

Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to balance patient preferences with clinical safety. We survey 335 individuals with lived mental health experience to collect preference rankings across therapeutic dimensions, then develop a multi-objective alignment framework using direct preference optimization. We train reward models for six criteria -- empathy, safety, active listening, self-motivated change, trust/rapport, and patient autonomy -- and systematically compare multi-objective approaches against single-objective optimization, supervised fine-tuning, and parameter merging. Multi-objective DPO (MODPO) achieves superior balance (77.6% empathy, 62.6% safety) compared to single-objective optimization (93.6% empathy, 47.8% safety), and therapeutic criteria outperform general communication principles by 17.2%. Blinded clinician evaluation confirms MODPO is consistently preferred, with LLM-evaluator agreement comparable to inter-clinician reliability.

Mehrab Beikzadeh, Yasaman Asadollah Salmanpour, Ashima Suvarna +4

Department of Computer Science, University of California, Los Angeles, CA, USA · Department of Psychology, The University of Texas at Austin, Austin, TX, USA · Department of Psychiatry, NYU Grossman School of Medicine, New York, NY, USA

Personalized Language Model AlignmentMulti-Objective Language Model AlignmentClinical Language Model EvaluationDirect Preference Optimization
AskPDF
Feb 17, 2026

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF), optimize for a single, global objective. While Group Relative Policy Optimization (GRPO) is a widely adopted on-policy reinforcement learning framework, its group-based normalization implicitly assumes that all samples are exchangeable, inheriting this limitation in personalized settings. This assumption conflates distinct user reward distributions and systematically biases learning toward dominant preferences while suppressing minority signals. To address this, we introduce Personalized GRPO (P-GRPO), a novel alignment framework that decouples advantage estimation from immediate batch statistics. By normalizing advantages against preference-group-specific reward histories rather than the concurrent generation group, P-GRPO preserves the contrastive signal necessary for learning distinct preferences. We evaluate P-GRPO across diverse tasks and find that it consistently achieves faster convergence and higher rewards than standard GRPO, thereby enhancing its ability to recover and align with heterogeneous preference signals. Our results demonstrate that accounting for reward heterogeneity at the optimization level is essential for building models that faithfully align with diverse human preferences without sacrificing general capabilities.

Jialu Wang, Heinrich Peters, Asad A. Butt +6

1Apple Inc., California, United States.

LLM AlignmentGroup Relative Policy OptimizationPersonalized Language Model AlignmentRL Post-TrainingPreference AlignmentPreference-Based RL
AskPDF
Dec 28, 2025

The Reward Model Selection Crisis in Personalized Alignment

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in deployment, computational constraints necessitate inference-time adaptation such as reward-guided decoding (RGD) rather than per-user policy fine-tuning. This creates a critical but overlooked requirement: reward models must not only rank preferences accurately but also effectively guide generation. We demonstrate that standard RM accuracy fails catastrophically as a selection criterion for deployment-ready personalized rewards. We introduce policy accuracy; a metric quantifying whether RGD-adapted LLMs correctly discriminate between preferred and dispreferred responses and show that upstream RM accuracy correlates only weakly with downstream policy accuracy (Kendall's tau = 0.08--0.31). More critically, we introduce Pref-LaMP the first personalized alignment benchmark with ground-truth user completions, enabling direct behavioural evaluation. On Pref-LaMP, we expose a complete decoupling between discriminative ranking and generation metrics: methods with 20-point RM accuracy differences produce almost identical output quality, and methods with high ranking accuracy can fail to generate behaviorally aligned responses. These findings reveal that the field has been optimizing for proxy metrics that do not predict deployment performance, and that current personalized alignment methods fail to operationalize preferences into behavioral adaptation under realistic deployment constraints. In contrast, we find simple in-context learning (ICL) to be highly effective - dominating all reward-guided methods for models ≥\geq3B parameters, achieving ∼\sim3 point ROUGE-1 gains over the best reward method at 7B scale.

Fady Rezk, Yuangang Pan, Chuan-Sheng Foo +4

School of Informatics, University of Edinburgh, UK · Agency for Science, Technology and Research (A*STAR), Singapore · Samsung AI Research Center, Cambridge, UK

Personalized Language Model AlignmentPersonalized Reward ModelingInference-Time Language Model AlignmentReward Model EvaluationLanguage Model Decoding
AskPDF
Oct 17, 2025

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

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.

Yizhuo Chen, Xin Liu, Ruijie Wang +7

University of Illinois Urbana-Champaign · Amazon · University of Notre Dame

LLM PersonalizationPersonalized Language ModelsPersonalized Language Model AlignmentLanguage Model Post-TrainingUser Preference Modeling
AskPDF