Where You Inject Diversity Matters: A Unified Framework for Diverse Generation
Open-ended generation tasks often require a set of meaningfully different outputs, yet large language models often produce similar generations. Existing test-time diversity methods operate at different stages of generation with varying effectiveness, but it remains unclear what design choices lead to meaningful diversity in the output. We introduce a framework that characterizes test-time diverse generation methods by the diversity source introduced during generation and provide a transmission score for measuring how effectively variation in the source reaches the final output. Guided by this framework, we propose fully automated specification-level generation methods that first generate diverse intermediate specifications and then condition on them to produce final responses. Across five open-ended tasks and four backbone models, specification-level injection improves output diversity over test-time baselines while maintaining comparable quality. Our analysis shows that successful diversity injection depends on both the diversity of the sources and their transmission to the output, highlighting source design and source-to-output realization as two key levers for building more diverse generation systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity
Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources.…
Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image Detection
The rapid proliferation of AI-generated images, powered by generative adversarial networks (GANs), diffusion models, and other synthesis techniques, has raised serious concerns about misinformation, copyright violations,…
On Diverse Asynchronous Activity Anticipation
We investigate the joint anticipation of long-term activity labels and their corresponding times with the aim of improving both the naturalness and diversity of predictions. We address these matters using Conditional Adv…
DiversityTowards Powerful Graph Neural Networks: Diversity Matters
Graph neural networks (GNNs) offer us an effective framework for graph representation learning via layer-wise neighborhood aggregation. Their success is attributed to their expressive power at learning representation of …
DiversityGraph Representation LearningNode ClassificationRepresentation LearningParametric Social Identity Injection and Diversification in Public Opinion Simulation
Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despite their scalability, current LLM-based s…