mlsanityData to 7 Oct 2026

Is Temperature the Creativity Parameter of Large Language Models?

arXiv 2405.00492 ↗First posted 1 May 2024cs.CL cs.AIcited by 92

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are applied to all sorts of creative tasks, and their outputs vary from beautiful, to peculiar, to pastiche, into plain plagiarism. The temperature parameter of an LLM regulates the amount of randomness, leading to more diverse outputs; therefore, it is often claimed to be the creativity parameter. Here, we investigate this claim using a narrative generation task with a predetermined fixed context, model and prompt. Specifically, we present an empirical analysis of the LLM output for different temperature values using four necessary conditions for creativity in narrative generation: novelty, typicality, cohesion, and coherence. We find that temperature is weakly correlated with novelty, and unsurprisingly, moderately correlated with incoherence, but there is no relationship with either cohesion or typicality. However, the influence of temperature on creativity is far more nuanced and weak than suggested by the "creativity parameter" claim; overall results suggest that the LLM generates slightly more novel outputs as temperatures get higher. Finally, we discuss ideas to allow more controlled LLM creativity, rather than relying on chance via changing the temperature parameter.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 5 of its 43 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

5 of 43 references.

References · 5

  1. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  2. 2020Trading Off Diversity and Quality in Natural Language Generationcited by 94
  3. 2023Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learningcited by 31
  4. 2024A Study on Large Language Models' Limitations in Multiple-Choice Question Answeringcited by 22
  5. 2023Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?cited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 46; 2026: 30.

92 papers.

Sort:

By area:

  1. 2024LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristicscited by 92
  2. 2025Jointly Reinforcing Diversity and Quality in Language Model Generationscited by 79
  3. 2025NoveltyBench: Evaluating Language Models for Humanlike Diversitycited by 64
  4. 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIscited by 63
  5. 2024Echoes in AI: Quantifying lack of plot diversity in LLM outputscited by 47
  6. 2025Exploring the Impact of Temperature on Large Language Models:Hot or Cold?cited by 40
  7. 2025CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Countingcited by 36
  8. 2024HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testingcited by 35
  9. 2025Roll the dice & look before you leap: Going beyond the creative limits of next-token predictioncited by 28
  10. 2025When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysiscited by 20
  11. 2024Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMscited by 17
  12. 2025Enhance-A-Video: Better Generated Video for Freecited by 11
38 more
  1. 2024Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Gamescited by 9
  2. 2025When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMscited by 9
  3. 2024FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formatscited by 8
  4. 2025Optimizing Diversity and Quality through Base-Aligned Model Collaborationcited by 8
  5. 2025Reflection-Window Decoding: Text Generation with Selective Refinementcited by 7
  6. 2025MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Modelscited by 7
  7. 2025Playing games with Large language models: Randomness and strategycited by 7
  8. 2025SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddingscited by 7
  9. 2025Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Modelscited by 7
  10. 2025EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMscited by 7
  11. 2025Improving Diversity in Language Models: When Temperature Fails, Change the Losscited by 7
  12. 2024Generating Diverse Hypotheses for Inductive Reasoningcited by 6
  13. 2025RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practicecited by 6
  14. 2025Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variabilitycited by 6
  15. 2025An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniquescited by 6
  16. 2025Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulationscited by 5
  17. 2026Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action Modelscited by 5
  18. 2024What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworkscited by 4
  19. 2024Mining Math Conjectures from LLMs: A Pruning Approachcited by 4
  20. 2025Enhancing Human-Like Responses in Large Language Modelscited by 4
  21. 2025Large Language Models for Extrapolative Modeling of Manufacturing Processescited by 4
  22. 2025WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosiscited by 4
  23. 2025Argument Summarization and its Evaluation in the Era of Large Language Modelscited by 4
  24. 2025Cognitive Agents Powered by Large Language Models for Agile Software Project Managementcited by 4
  25. 2024Can LLMs plan paths with extra hints from solvers?cited by 3
  26. 2024CaLMFlow: Volterra Flow Matching using Causal Language Modelscited by 3
  27. 2024Generating Energy-efficient code with LLMscited by 3
  28. 2025Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratingscited by 3
  29. 2026Language of Thought Shapes Output Diversity in Large Language Modelscited by 3
  30. 2026Within-Model vs Between-Prompt Variability in Large Language Models for Creative Taskscited by 3
  31. 2026Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Modelscited by 3
  32. 2024Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrievalcited by 2
  33. 2025Exploring Large Language Models for Translating Romanian Computational Problems into Englishcited by 2
  34. 2025Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Softwarecited by 2
  35. 2025DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generationcited by 2
  36. 2025Automated Business Process Analysis: An LLM-Based Approach to Value Assessmentcited by 2
  37. 2025Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Modelscited by 2
  38. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEscited by 2

50 most cited of 92 All 92 (JSON)