Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with variable weights at inference time for truly personalized models presents a significant challenge. Existing approaches are either computationally expensive to train or do not sufficiently steer model behaviors. This paper introduces the Multi-Objective Online DPO (MO-ODPO) algorithm, designed to robustly and efficiently align model behaviors with multiple, potentially conflicting human preferences. Our approach incorporates a prompt conditioning mechanism, allowing us to train a single preference-conditional policy, that can adapt to new preference combinations at inference. Experiments on two popular benchmarks show that MO-ODPO Pareto-dominates existing baselines while providing excellent inference-time steerability between diverse objectives.

At present, most of the prediction studies related to antagonistic event-group competitions focus on the prediction of competition results, and less on the prediction of the competition process, which can not provide real-time feedback of the athletes' state information in the actual competition, and thus can not analyze the changes of the competition situation. In order to solve this problem, this paper proposes a prediction model based on Random Forest for the turning point of the antagonistic event-group. Firstly, the quantitative equation of competitive potential energy is proposed; Secondly, the quantitative value of competitive potential energy is obtained by using the dynamic combination of weights method, and the turning point of the competition situation of the antagonistic event-group is marked according to the quantitative time series graph; Finally, the random forest prediction model based on the optimisation of the KM-SMOTE algorithm and the grid search method is established. The experimental analysis shows that: The quantitative equation of competitive potential energy can effectively reflect the dynamic situation of the competition; The model can effectively predict the turning point of the competition situation of the antagonistic event-group, and the recall rate of the model in the test set is 86.13%; The model has certain significance for the future study of the competition situation of the antagonistic event-group.

This paper proposes a grey interval relation TOPSIS method for the decision making in which all of the attribute weights and attribute values are given by the interval grey numbers. In this paper, all of the subjective and objective weights are obtained by interval grey number and decision-making is based on four methods such as the relative approach degree of grey TOPSIS, the relative approach degree of grey incidence and the relative approach degree method using the maximum entropy estimation using 2-dimensional Euclidean distance. A multiple attribute decision-making example for evaluation of artistic talent of Kayagum (stringed Korean harp) players is given to show practicability of the proposed approach.

This paper proposes a grey interval relation TOPSIS for the decision making in which all of the attribute weights and attribute values are given by the interval grey numbers. The feature of our method different from other grey relation decision-making is that all of the subjective and objective weights are obtained by interval grey number and that decisionmaking is performed based on the relative approach degree of grey TOPSIS, the relative approach degree of grey incidence and the relative membership degree of grey incidence using 2-dimensional Euclidean distance. The weighted Borda method is used for combining the results of three methods. An example shows the applicability of the proposed approach.