mlsanityData to 7 Oct 2026

Anchorless Diversification for Parallel LLM Ideation

arXiv 2605.30150 ↗First posted 28 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

LLMs are increasingly used to generate candidate-idea pools for creative tasks where broad exploration is valuable. Parallel inference can be attractive in this setting when it broadens the pool while retaining quality and cost efficiency. We study inference-time controls for candidate-pool diversification, asking whether anchorless methods can rival methods that depend on observed seed ideas. Across three creative task families, we compare independent generation and semantic direction stratification with self-, peer-, and representative-anchor baselines, under neutral and population-referential divergent instructions. Population-referential divergence is a strong low-cost baseline, increasing semantic diversity while preserving quality proxies. Semantic direction stratification is stronger: a single planning call organizes generations across broad semantic directions, yielding the best diversity--quality--compute frontier. Anchored regeneration can be strong in final-pool diversity, but its advantage shrinks under full-pipeline token accounting. These results establish practical anchorless baselines for open-ended LLM ideation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

31 of 53 references.

References · 31

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  4. 2018Hierarchical Neural Story Generationcited by 1,182
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  6. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  7. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  8. 2023Does Writing with Language Models Reduce Content Diversity?cited by 190
  9. 2023Generative artificial intelligence enhances creativity but reduces the diversity of novel contentcited by 165
  10. 2020Evaluating the Evaluation of Diversity in Natural Language Generationcited by 127
  11. 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
  12. 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
19 more
  1. 2023The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Textcited by 97
  2. 2020Trading Off Diversity and Quality in Natural Language Generationcited by 94
  3. 2019Comparison of Diverse Decoding Methods from Conditional Language Modelscited by 78
  4. 2025NoveltyBench: Evaluating Language Models for Humanlike Diversitycited by 64
  5. 2025Evaluating the Diversity and Quality of LLM Generated Contentcited by 51
  6. 2024Forcing Diffuse Distributions out of Language Modelscited by 48
  7. 2024Echoes in AI: Quantifying lack of plot diversity in LLM outputscited by 47
  8. 2023Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Votingcited by 46
  9. 2025The Price of Format: Diversity Collapse in LLMscited by 43
  10. 2024EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Samplingcited by 42
  11. 2024Weaver: Foundation Models for Creative Writingcited by 25
  12. 2025Creativity in LLM-based Multi-Agent Systems: A Surveycited by 23
  13. 2024Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learningcited by 19
  14. 2025G2: Guided Generation for Enhanced Output Diversity in LLMscited by 14
  15. 2024Creative Beam Search: LLM-as-a-Judge For Improving Response Generationcited by 13
  16. 2025Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Modelscited by 9
  17. 2025MuseScorer: Idea Originality Scoring At Scalecited by 2
  18. 2026From semantic memory to collective creativity: A generative cognitive foundation for social creativity modelscited by 2
  19. 2026Ex Ante Evaluation of AI-Induced Idea Diversity Collapsecited by 1

Built on by

Not cited yet.