Reinforcement learning from human feedback (RLHF) aligns Large Language Models (LLMs) with human preferences. However, these preferences can often change over time due to external factors (e.g. environment change and societal influence). Consequently, what was wrong then might be right now. Current preference optimization algorithms do not account for temporal preference drift in their modeling, which can lead to severe misalignment. To address this limitation, we use a Dynamic Bradley-Terry model that models preferences via time-dependent reward functions, and propose Non-Stationary Direct Preference Optimisation (NS-DPO). By introducing a discount parameter in the loss function, NS-DPO applies exponential weighting, which proportionally focuses learning on more time-relevant datapoints. We theoretically analyse the convergence of NS-DPO in the offline setting, providing upper bounds on the estimation error caused by non-stationary preferences. Finally, we demonstrate the effectiveness of NS-DPO1 for fine-tuning LLMs in scenarios with drifting preferences. By simulating preference drift using renowned reward models and modifying popular LLM datasets accordingly, we show that NS-DPO fine-tuned LLMs remain robust under non-stationarity, significantly outperforming baseline algorithms that ignore temporal preference changes, without sacrificing performance in stationary cases.

Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits the performance of job recommendations. The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. Specifically, BISTRO is composed of three stages: 1) coarse-grained semantic clustering, 2) fine-grained job preference extraction, and 3) personalized top-$k$ job recommendation. Initially, BISTRO segments the user interaction sequence into sessions and leverages session-based semantic clustering to achieve broad identification of person-job matching. Subsequently, we design a hypergraph wavelet learning method to capture the nuanced job preference drift. To mitigate the effect of noise in interactions caused by frequent preference drift, we innovatively propose an adaptive wavelet filtering technique to remove noisy interaction. Finally, a recurrent neural network is utilized to analyze session-based interaction for inferring personalized preferences. Extensive experiments on three real-world offline recruitment datasets demonstrate the significant performances of our framework. Significantly, BISTRO also excels in online experiments, affirming its effectiveness in live recruitment settings. This dual success underscores the robustness and adaptability of BISTRO. The source code is available at https://github.com/Applied-Machine-Learning-Lab/BISTRO.