Zhen-Yu Zhang, Jerry Huang, Gang Niu, Takashi Ishida, Masashi Sugiyama
原文摘要
Preference alignment has become a central tool to align large language models (LLMs) with human values and desired behavior, and its online variant can further advance their capabilities beyond what static data alone offer by repeatedly generating and labeling new responses with human feedback. But costly, time-consuming annotations limit its scalability, making sample efficiency essential, and existing methods typically seek to improve it by expanding coverage of the response space or selecting pairs with the highest uncertainty for comparison. Although they are effective, these methods quantify uncertainty from the perspective of the LLM, which may differ from the uncertainty perceived by the user: a pair can appear highly uncertain to the LLM even when past comparisons from the user already imply a clear ordering. In this paper, we propose multidimensional preference-guided online direct preference optimization (MPG-DPO), which leverages low-cost multidimensional evaluations from automated verifiers on the user historical comparisons to construct a personalized preference cone guiding response selection for online preference alignment. Specifically, it first discards responses that are confidently dominated under the estimated user preference, then selects two responses that are competitive under the retained preference cone yet exhibit the strongest unresolved disagreement. Theoretical analysis shows that, with high probability, the fraction of queries spent on cone-dominated responses vanishes as learning progresses. Experiments across multiple LLM families show that MPG-DPO outperforms strong contenders under matched query budgets.
Mohit Sharma, Okan Koç, Amit Deshpande, Takashi Ishida, Gang Niu, Rajiv Ratn Shah, Masashi Sugiyama
原文摘要
There is a fundamental limit to the best prediction error of any model for a given data distribution. In classification, the Bayes error quantifies this limit and serves as both a benchmark for trained models and a criterion to detect overfitting. The state-of-the-art Bayes error estimation techniques for binary classification use only soft labels (positive class probabilities) and require no input features or auxiliary training. We extend such notions to constrained classification problems, such as fairness. Fair classification is an important case of constrained or multi-objective classification. It requires a model not only to be accurate but also to yield fair outcomes (equal or near-equal true positive rates) across different demographic groups (e.g., race and gender). This leads to an inherent fairness-accuracy tradeoff or a Pareto frontier that is used to compare fair classifiers against each other. The focus of our work is to estimate the fundamental limit for this fairness-accuracy tradeoff. We derive an explicit expression for the fair Bayes error rate (i.e., best achievable error rate subject to given fairness constraints), and construct consistent, instance-free estimators for it using only soft labels and group information. We provably bound the bias and the sample complexity of our estimators. Empirically, our method produces a robust, low-variance estimate of the optimal fairness-accuracy tradeoff curve, even when the soft labels are noisy and derived from a classification model on hard labels.
Abudukelimu Wuerkaixi, Qizhou Wang, Sen Cui, Wutong Xu, Bo Han, Gang Niu, Masashi Sugiyama, Changshui Zhang
原文摘要
With the growing deployment of large language models (LLMs) across diverse domains, concerns regarding their safety have grown substantially. LLM unlearning has emerged as a pivotal approach to removing harmful or unlawful content while maintaining utility. Despite increasing interest, the challenges of continual unlearning, which is common in real-world scenarios, remain underexplored. Successive unlearning tasks often lead to intensified utility degradation. To effectively unlearn targeted knowledge while preserving LLM utility, it is essential to minimize changes in model parameters by selectively updating those linked to the target knowledge, thereby ensuring other knowledge remains unaffected. Building on the task vector framework, we propose a new method named ALKN (Adaptive Localization of Knowledge Negation), which uses dynamic masking to sparsify training gradients and adaptively adjusts unlearning intensity based on inter-task relationships. Comprehensive experiments across three well-established LLM unlearning datasets demonstrate that our approach consistently outperforms baseline methods in both unlearning effectiveness and utility retention under continual unlearning settings.