Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity
Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions under which personalized alignment achieves O(1) online regret and log(1/epsilon) offline sample complexity. We show that these optimal rates depend on a specific user-diversity condition: the population of user-specific heads must span the latent reward directions that can alter the optimal response. We prove that this condition is both necessary and sufficient. When it holds, simple greedy algorithms achieve benchmark efficiency; when it fails, every learner in a natural admissible class incurs at least logarithmic regret. Our results identify user diversity as the fundamental driver of personalized identifiability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-…
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial int…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs
Large Language Models (LLMs) are prone to sycophantic behavior, uncritically conforming to user beliefs. As models increasingly condition responses on user-specific context (personality traits, preferences, conversation …
Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
Chain-of-Thought (CoT) prompting plays an indispensable role in endowing large language models (LLMs) with complex reasoning capabilities. However, CoT currently faces two fundamental challenges: (1) Sufficiency, which e…
Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning
Sentiment expression in microblog posts can be affected by user{'}s personal character, opinion bias, political stance and so on. Most of existing personalized microblog sentiment classification methods suffer from the i…
General ClassificationMulti-Task LearningSentiment AnalysisSentiment Classification