# Is Temperature the Creativity Parameter of Large Language Models?

arXiv: https://arxiv.org/abs/2405.00492 · HTML: https://mlsanity.com/paper/2405.00492/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 43 references that are in the map.
- First posted on arXiv 1 May 2024.

## Builds on (most cited first, 5 of 5)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Trading Off Diversity and Quality in Natural Language Generation](https://mlsanity.com/paper/2004.10450/) (2020)
- [Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning](https://mlsanity.com/paper/2310.13486/) (2023)
- [A Study on Large Language Models' Limitations in Multiple-Choice Question Answering](https://mlsanity.com/paper/2401.07955/) (2024)
- [Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?](https://mlsanity.com/paper/2310.05079/) (2023)

## Built on by (most cited first, 30 of 93)

- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [Echoes in AI: Quantifying lack of plot diversity in LLM outputs](https://mlsanity.com/paper/2501.00273/) (2024)
- [Exploring the Impact of Temperature on Large Language Models:Hot or Cold?](https://mlsanity.com/paper/2506.07295/) (2025)
- [CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting](https://mlsanity.com/paper/2504.15485/) (2025)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis](https://mlsanity.com/paper/2501.10604/) (2025)
- [Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs](https://mlsanity.com/paper/2409.11547/) (2024)
- [Enhance-A-Video: Better Generated Video for Free](https://mlsanity.com/paper/2502.07508/) (2025)
- [Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games](https://mlsanity.com/paper/2410.21359/) (2024)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats](https://mlsanity.com/paper/2408.08841/) (2024)
- [Reflection-Window Decoding: Text Generation with Selective Refinement](https://mlsanity.com/paper/2502.03678/) (2025)
- [SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings](https://mlsanity.com/paper/2503.19257/) (2025)
- [Optimizing Diversity and Quality through Base-Aligned Model Collaboration](https://mlsanity.com/paper/2511.05650/) (2025)
- [MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models](https://mlsanity.com/paper/2502.20933/) (2025)
- [Playing games with Large language models: Randomness and strategy](https://mlsanity.com/paper/2503.02582/) (2025)
- [Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models](https://mlsanity.com/paper/2504.02902/) (2025)
- [EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs](https://mlsanity.com/paper/2505.17139/) (2025)
- [An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques](https://mlsanity.com/paper/2507.05123/) (2025)
- [Improving Diversity in Language Models: When Temperature Fails, Change the Loss](https://mlsanity.com/paper/2508.09654/) (2025)
- [Generating Diverse Hypotheses for Inductive Reasoning](https://mlsanity.com/paper/2412.13422/) (2024)
- [RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practice](https://mlsanity.com/paper/2502.14930/) (2025)
- [Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability](https://mlsanity.com/paper/2504.12320/) (2025)
- [Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations](https://mlsanity.com/paper/2501.16356/) (2025)
- [Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action Models](https://mlsanity.com/paper/2602.04184/) (2026)
- [What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks](https://mlsanity.com/paper/2407.03007/) (2024)

## 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.