D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard autoregressive search procedures, such as beam search, do not directly apply to iterative denoising, where hypotheses are complete intermediate sequences rather than left-to-right prefixes. Furthermore, existing diffusion decoding procedures only provide limited control over the diversity and coverage of retained hypotheses. In this work, we introduce D5P4, a beam-style decoding method tailored to discrete diffusion models, which casts intermediate beam selection as MAP inference under a partitioned Determinantal Point Process. This yields a model-internal batch objective that balances quality and diversity without external verifiers. Experiments on open-ended generation, question answering, and mathematical reasoning show that D5P4 improves diversity and pass@$k$ coverage while matching or surpassing baseline quality and fidelity
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningQuestion AnsweringText GenerationSimilar Papers 제목 키워드 기반
Determinantal consensus clustering
Random restart of a given algorithm produces many partitions to yield a consensus clustering. Ensemble methods such as consensus clustering have been recognized as more robust approaches for data clustering than single c…
ClusteringClustering EnsembleDiversityPoint ProcessesOn Sampling and Greedy MAP Inference of Constrained Determinantal Point Processes
Subset selection problems ask for a small, diverse yet representative subset of the given data. When pairwise similarities are captured by a kernel, the determinants of submatrices provide a measure of diversity or indep…
ClusteringDiversityPoint ProcessesA New Many-Objective Evolutionary Algorithm Based on Determinantal Point Processes
To handle different types of Many-Objective Optimization Problems (MaOPs), Many-Objective Evolutionary Algorithms (MaOEAs) need to simultaneously maintain convergence and population diversity in the high-dimensional obje…
DiversityEvolutionary AlgorithmsPoint ProcessesOpen Loop Hyperparameter Optimization and Determinantal Point Processes
Driven by the need for parallelizable hyperparameter optimization methods, this paper studies \emph{open loop} search methods: sequences that are predetermined and can be generated before a single configuration is evalua…
DiversityHyperparameter OptimizationPoint ProcessesBatched Gaussian Process Bandit Optimization via Determinantal Point Processes
Gaussian Process bandit optimization has emerged as a powerful tool for optimizing noisy black box functions. One example in machine learning is hyper-parameter optimization where each evaluation of the target function r…
Bayesian OptimizationDiversityPoint Processes