EXACT: Explicit Attribute-Guided Decoding-Time Personalization

• URL: http://arxiv.org/abs/2602.17695v1
• Date: Fri, 06 Feb 2026 14:53:37 GMT
• Title: EXACT: Explicit Attribute-Guided Decoding-Time Personalization
• Authors: Xin Yu, Hanwen Xing, Lingzhou Xue,
• Abstract summary: EXACT is a new decoding-time personalization that aligns generation with limited pairwise preference feedback.<n>We show that EXACT consistently outperforms strong baselines, including preference modeling accuracy and personalized generation quality.
• Score: 11.035465374731563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Achieving personalized alignment requires adapting large language models to each user's evolving context. While decoding-time personalization offers a scalable alternative to training-time methods, existing methods largely rely on implicit, less interpretable preference representations and impose a rigid, context-agnostic user representation, failing to account for how preferences shift across prompts. We introduce EXACT, a new decoding-time personalization that aligns generation with limited pairwise preference feedback using a predefined set of interpretable attributes. EXACT first identifies user-specific attribute subsets by maximizing the likelihood of preferred responses in the offline stage. Then, for online inference, EXACT retrieves the most semantically relevant attributes for an incoming prompt and injects them into the context to steer generation. We establish theoretical approximation guarantees for the proposed algorithm under mild assumptions, and provably show that our similarity-based retrieval mechanism effectively mitigates contextual preference shifts, adapting to disparate tasks without pooling conflicting preferences. Extensive experiments on human-annotated preference datasets demonstrate that EXACT consistently outperforms strong baselines, including preference modeling accuracy and personalized generation quality.

Related papers

• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
  RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-01-29T12:14:31Z)
• Automatic Prompt Optimization for Dataset-Level Feature Discovery [38.37728428959515]
  We formulate feature discovery as a dataset-level prompt optimization problem.<n>We propose a multi-agent prompt optimization framework in which language-model agents jointly propose feature definitions, extract feature values, and evaluate feature quality.<n>This formulation departs from prior prompt optimization methods that rely on per-sample supervision and provides a principled mechanism for automatic feature discovery from unstructured text.
  arXiv  Detail & Related papers  (2026-01-20T12:51:03Z)
• Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection [50.68751788132789]
  This study introduces an innovative methodology named as Weighted Semantic Map with Auto-adaptive Candidate Editing Network (WSAE-Net)<n>The generation of the weighted semantic map is designed to maximize the reduction of non-semantic feature units that need to be computed.<n>The auto-adaptive candidate editing sequences are designed to determine the optimal computational order among the feature units to be processed.
  arXiv  Detail & Related papers  (2025-11-17T05:34:10Z)
• Inference-Time Personalized Alignment with a Few User Preference Queries [24.28598841525897]
  We study the problem of aligning a generative model's response with a user's preferences.<n>We propose UserAlign, that elicits the user's preferences with a few queries as pairwise response comparisons.
  arXiv  Detail & Related papers  (2025-11-04T20:07:03Z)
• POPI: Personalizing LLMs via Optimized Natural Language Preference Inference [42.25870704040321]
  POPI is a general framework that introduces a preference inference model to distill heterogeneous user signals into concise natural language summaries.<n>These summaries act as transparent, compact, and transferable personalization representations that condition a shared generation model to produce personalized responses.<n>Extensive experiments across four personalization benchmarks demonstrate that POPI consistently improves personalization accuracy while reducing context overhead by a large margin.
  arXiv  Detail & Related papers  (2025-10-17T23:07:57Z)
• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It [81.50711040539566]
  Current large language model (LLM) development treats task-solving and preference alignment as separate challenges.<n>We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks.<n>Our framework creates scenarios where identical questions require different reasoning chains depending on user context.
  arXiv  Detail & Related papers  (2025-09-30T18:55:28Z)
• What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context [56.590259941275434]
  RecPO is a preference optimization framework for sequential recommendation.<n>It exploits adaptive reward margins based on inferred preference hierarchies and temporal signals.<n>It mirrors key characteristics of human decision-making: favoring timely satisfaction, maintaining coherent preferences, and exercising discernment under shifting contexts.
  arXiv  Detail & Related papers  (2025-06-02T21:09:29Z)
• Towards Explainable Temporal User Profiling with LLMs [3.719862246745416]
  We leverage large language models (LLMs) to generate natural language summaries of users' interaction histories.<n>Our framework not only models temporal user preferences but also produces natural language profiles that can be used to explain recommendations in an interpretable manner.
  arXiv  Detail & Related papers  (2025-05-01T22:02:46Z)
• Preference Discerning with LLM-Enhanced Generative Retrieval [23.559962422900238]
  In sequential recommendation, models recommend items based on user's interaction history.<n>We propose a new paradigm, namely preference discerning, which explicitly conditions a generative recommendation model on user preferences.<n>Our results show that Mender effectively adapts its recommendation guided by human preferences, even if not observed during training.
  arXiv  Detail & Related papers  (2024-12-11T18:26:55Z)
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback [70.32795295142648]
  Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step. Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
  arXiv  Detail & Related papers  (2024-01-21T10:46:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.