Search papers, labs, and topics across Lattice.
This paper addresses the challenge of learning mixtures of Plackett-Luce models from multi-way ranking responses, particularly when underlying preferences are heterogeneous. The authors introduce MoPLEx, an efficient algorithm that combines augmented ranking responses generated by a language model with a gradient-based estimation approach to fit these mixture models. Experimental results indicate that MoPLEx significantly enhances clustering and ranking accuracy, outperforming existing methods by 43.7% and 15.2% respectively on preference optimization datasets, while maintaining low estimation error.
MoPLEx achieves up to 43.7% improvement in clustering accuracy by effectively learning from complex multi-way rankings, revealing the power of leveraging language models for preference optimization.
We consider the problem of learning a mixture of $k$ Plackett-Luce models given multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has many applications in AI alignment and preference optimization. Prior work has studied mixtures of Bradley-Terry models from pairwise comparisons. However, uncovering mixture models is theoretically unidentifiable when $k$ exceeds $m/2$, where $m$ is the length of a ranking. We propose an efficient implementation to address this limitation, which involves first augmenting the rankings to a larger size by generating new responses from a base language model, followed by a gradient-based estimation to reduce inference cost in the input embedding space. Based on this procedure, we then design an expectation-maximization algorithm with these two steps to fit a mixture of Plackett-Luce models, called MoPLEx. Extensive experiments are conducted to verify this approach. First, we show that the gradient-based approximation estimates true probabilities with less than 5% error on models with up to 34 billion parameters. Second, we show that MoPLEx improves clustering and ranking accuracy by an average of 43.7% and 15.2% over baselines using single ranking and mixtures of Bradley-Terry models, on preference optimization datasets. These results demonstrate the effectiveness of MoPLEx for tackling multi-way rankings from heterogeneous preferences through measuring alignment between gradients.
