mlsanityData to 7 Oct 2026

LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play

arXiv 2405.06373 ↗First posted 10 May 2024cs.CL cs.AIcited by 65

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions. To enhance LLM creativity, our key insight is to emulate the human process of inducing collective creativity through engaging discussions with participants from diverse backgrounds and perspectives. To this end, we propose LLM Discussion, a three-phase discussion framework that facilitates vigorous and diverging idea exchanges and ensures convergence to creative answers. Moreover, we adopt a role-playing technique by assigning distinct roles to LLMs to combat the homogeneity of LLMs. We evaluate the efficacy of the proposed framework with the Alternative Uses Test, Similarities Test, Instances Test, and Scientific Creativity Test through both LLM evaluation and human study. The results show that our proposed framework outperforms single-LLM approaches and existing multi-LLM frameworks across various creativity metrics. The code is available at https://github.com/lawraa/LLM-Discussion.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

40 of 55 references.

References · 40

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  11. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  12. 2023Large Language Models as Optimizerscited by 830
28 more
  1. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  2. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  3. 2023Instruction Tuning with GPT-4cited by 676
  4. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  5. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  7. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 420
  8. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 416
  9. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  10. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  11. 2023Role-Play with Large Language Modelscited by 290
  12. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  13. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
  14. 2023Does Writing with Language Models Reduce Content Diversity?cited by 190
  15. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  16. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 173
  17. 2023Art or Artifice? Large Language Models and the False Promise of Creativitycited by 168
  18. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  19. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 143
  20. 2023A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writingcited by 98
  21. 2022Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writerscited by 69
  22. 2023TinyGSM: achieving >80% on GSM8k with small language modelscited by 68
  23. 2022Putting GPT-3's Creativity to the (Alternative Uses) Testcited by 62
  24. 2023ChatHaruhi: Reviving Anime Character in Reality via Large Language Modelcited by 57
  25. 2023Multi-Party Chat: Conversational Agents in Group Settings with Humans and Modelscited by 53
  26. 2023ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPTcited by 32
  27. 2023Using GPT-4 to Augment Unbalanced Data for Automatic Scoringcited by 20
  28. 2023Thespian: Multi-Character Text Role-Playing Game Agentscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 30; 2026: 20.

65 papers.

Sort:

By area:

  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  2. 2024Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Charactercited by 61
  3. 2024Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinkingcited by 43
  4. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 40
  5. 2024Benchmarking Language Model Creativity: A Case Study on Code Generationcited by 38
  6. 2024Reverse Thinking Makes LLMs Stronger Reasonerscited by 29
  7. 2024Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publicationscited by 26
  8. 2025LLM Probability Concentration: How Alignment Shrinks the Generative Horizoncited by 26
  9. 2025MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultationcited by 25
  10. 2025Creativity in LLM-based Multi-Agent Systems: A Surveycited by 23
  11. 2025VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcarecited by 17
  12. 2024Training Language Models to Win Debates with Self-Play Improves Judge Accuracycited by 16
38 more
  1. 2024GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancycited by 14
  2. 2024A Survey on Human-Centric LLMscited by 13
  3. 2026Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinementcited by 13
  4. 2025Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learningcited by 12
  5. 2024GPT for Games: An Updated Scoping Review (2020-2024)cited by 10
  6. 2024Fairness Testing of Large Language Models in Role-Playingcited by 10
  7. 2025United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theorycited by 10
  8. 2025BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generationcited by 10
  9. 2025MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaborationcited by 9
  10. 2025Diversity-Enhanced Reasoning for Subjective Questionscited by 9
  11. 2025Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learningcited by 9
  12. 2025The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agentscited by 8
  13. 2025Optimizing Diversity and Quality through Base-Aligned Model Collaborationcited by 8
  14. 2024PersLLM: A Personified Training Approach for Large Language Modelscited by 6
  15. 2025Adaptive Helpfulness-Harmlessness Alignment with Preference Vectorscited by 6
  16. 2025MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Frameworkcited by 6
  17. 2024The Drama Machine: Simulating Character Development with LLM Agentscited by 5
  18. 2025Role-Playing Evaluation for Large Language Modelscited by 5
  19. 2025AI Agent Behavioral Sciencecited by 5
  20. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMscited by 5
  21. 2025MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collectionscited by 4
  22. 2026LLM Review: Enhancing Creative Writing via Blind Peer Review Feedbackcited by 4
  23. 2026DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttalcited by 4
  24. 2025Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layerscited by 3
  25. 2025Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Riskscited by 3
  26. 2025ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilitiescited by 3
  27. 2026MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systemscited by 3
  28. 2026Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversationscited by 3
  29. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  30. 2024Problem-Solving in Language Model Networkscited by 2
  31. 2025Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Modelscited by 2
  32. 2025Critical Confabulation: Can LLMs Hallucinate for Social Good?cited by 2
  33. 2025Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinationscited by 2
  34. 2025Enhancing Diversity of LLM-Generated Educational Taskscited by 2
  35. 2026Context Learning for Multi-Agent Discussioncited by 2
  36. 2026Automated Creativity Evaluation of Language Models Across Open-Ended Taskscited by 2
  37. 2025AD-GPT: Large Language Models in Alzheimer's Diseasecited by 1
  38. 2025Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Taskscited by 1

50 most cited of 65 All 65 (JSON)