Where You Inject Diversity Matters: A Unified Framework for Diverse Generation

• URL: http://arxiv.org/abs/2606.10302v1
• Date: Tue, 09 Jun 2026 01:40:44 GMT
• Title: Where You Inject Diversity Matters: A Unified Framework for Diverse Generation
• Abstract summary: We introduce a framework that characterizes test-time diverse generation methods by the diversity source introduced during generation.<n>We propose fully automated specification-level generation methods that first generate diverse intermediate specifications and then condition on them to produce final responses.<n>Our analysis shows that successful diversity injection depends on both the diversity of the sources and their transmission to the output.
• Score: 11.157357341000248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing [78.70918589095639]
  Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity.<n>This paper proposes an RL framework structured around a semi-structured long Chain-of-Thought (CoT)<n>We introduce a Diverse Planning Branching method that strategically introduces divergence at the planning phase based on diversity variation.
  arXiv  Detail & Related papers  (2026-01-14T16:30:20Z)
• G2: Guided Generation for Enhanced Output Diversity in LLMs [22.52615993477612]
  Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks.<n>LLMs exhibit a critical limitation in output diversity, often generating highly similar content across multiple attempts.<n>We propose Guide-to-Generation (G2), a training-free plug-and-play method that enhances output diversity while preserving generation quality.
  arXiv  Detail & Related papers  (2025-11-01T07:13:28Z)
• Jointly Reinforcing Diversity and Quality in Language Model Generations [64.72289248044514]
  Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity.<n>We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimize for response quality and semantic diversity.
  arXiv  Detail & Related papers  (2025-09-02T17:38:47Z)
• Evaluating the Diversity and Quality of LLM Generated Content [72.84945252821908]
  We introduce a framework for measuring effective semantic diversity--diversity among outputs that meet quality thresholds.<n>Although preference-tuned models exhibit reduced lexical and syntactic diversity, they produce greater effective semantic diversity than SFT or base models.<n>These findings have important implications for applications that require diverse yet high-quality outputs.
  arXiv  Detail & Related papers  (2025-04-16T23:02:23Z)
• Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning [28.654890118684957]
  Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge. The diversity of the generation is equally important because it reflects the model's ability to use a range of commonsense knowledge facts. We propose a simple method that diversifies the LLM generations, while preserving their quality.
  arXiv  Detail & Related papers  (2024-04-25T17:52:39Z)
• Diversify Question Generation with Retrieval-Augmented Style Transfer [68.00794669873196]
  We propose RAST, a framework for Retrieval-Augmented Style Transfer. The objective is to utilize the style of diverse templates for question generation. We develop a novel Reinforcement Learning (RL) based approach that maximizes a weighted combination of diversity reward and consistency reward.
  arXiv  Detail & Related papers  (2023-10-23T02:27:31Z)
• VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder [38.35049378875308]
  We introduce VOLTA, a framework that elevates generative diversity by bridging Transformer with VAE. We perform comprehensive experiments with two types of Transformers on six datasets to show that our approach can significantly improve generative diversity while maintaining generative quality.
  arXiv  Detail & Related papers  (2023-07-03T08:45:42Z)
• Contrastive Learning for Diverse Disentangled Foreground Generation [67.81298739373766]
  We introduce a new method for diverse foreground generation with explicit control over various factors. We leverage contrastive learning with latent codes to generate diverse foreground results for the same masked input. Experiments demonstrate the superiority of our method over state-of-the-arts in result diversity and generation controllability.
  arXiv  Detail & Related papers  (2022-11-04T18:51:04Z)
• Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search [111.06379262544911]
  We compare the output diversity of a quality diversity evolutionary search performed in two different search spaces. A learned model is better at interpolating between known data points than at extrapolating or expanding towards unseen examples.
  arXiv  Detail & Related papers  (2021-05-10T10:27:43Z)
• Informed Sampling for Diversity in Concept-to-Text NLG [8.883733362171034]
  We propose an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce. Specifically, we augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output.
  arXiv  Detail & Related papers  (2020-04-29T17:43:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.