# CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints

arXiv: https://arxiv.org/abs/2410.04197 · HTML: https://mlsanity.com/paper/2410.04197/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 60 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 30 of 41)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [Unifying Human and Statistical Evaluation for Natural Language Generation](https://mlsanity.com/paper/1904.02792/) (2019)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://mlsanity.com/paper/2210.17546/) (2022)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [The Generative AI Paradox: "What It Can Create, It May Not Understand"](https://mlsanity.com/paper/2311.00059/) (2023)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization](https://mlsanity.com/paper/2405.16455/) (2024)
- [SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore](https://mlsanity.com/paper/2308.04430/) (2023)
- [COLLIE: Systematic Construction of Constrained Text Generation Tasks](https://mlsanity.com/paper/2307.08689/) (2023)
- [Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers](https://mlsanity.com/paper/2211.05030/) (2022)
- [Can Large Language Models Understand Real-World Complex Instructions?](https://mlsanity.com/paper/2309.09150/) (2023)
- [CFBench: A Comprehensive Constraints-Following Benchmark for LLMs](https://mlsanity.com/paper/2408.01122/) (2024)

## Built on by (most cited first, 24 of 24)

- [Shifting Long-Context LLMs Research from Input to Output](https://mlsanity.com/paper/2503.04723/) (2025)
- [Does quantization affect models' performance on long-context tasks?](https://mlsanity.com/paper/2505.20276/) (2025)
- [CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges](https://mlsanity.com/paper/2603.11863/) (2026)
- [Frankentext: Stitching random text fragments into long-form narratives](https://mlsanity.com/paper/2505.18128/) (2025)
- [Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models](https://mlsanity.com/paper/2510.12110/) (2025)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Evaluating the Creativity of LLMs in Persian Literary Text Generation](https://mlsanity.com/paper/2509.18401/) (2025)
- [Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations](https://mlsanity.com/paper/2605.13596/) (2026)
- [Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation](https://mlsanity.com/paper/2508.18709/) (2025)
- [Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety](https://mlsanity.com/paper/2509.12936/) (2025)
- [NARRA-Gym for Evaluating Interactive Narrative Agents](https://mlsanity.com/paper/2605.08503/) (2026)
- [Leveraging Large Models to Evaluate Novel Content: A Case Study on Advertisement Creativity](https://mlsanity.com/paper/2503.00046/) (2025)
- [Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed Story Retelling](https://mlsanity.com/paper/2601.17226/) (2026)
- [High-quality generation of dynamic game content via small language models: A proof of concept](https://mlsanity.com/paper/2601.23206/) (2026)
- [PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts](https://mlsanity.com/paper/2603.21438/) (2026)
- [UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning](https://mlsanity.com/paper/2604.05517/) (2026)
- [How Creative Are Large Language Models in Generating Molecules?](https://mlsanity.com/paper/2604.18031/) (2026)
- [Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation](https://mlsanity.com/paper/2606.12599/) (2026)
- [Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation](https://mlsanity.com/paper/2608.05576/) (2026)
- [UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following](https://mlsanity.com/paper/2608.09154/) (2026)
- [Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models](https://mlsanity.com/paper/2609.22152/) (2026)
- [Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs](https://mlsanity.com/paper/2609.30492/) (2026)
- [The Effects of Incremental Instruction Delivery on Language-Model Creative Writing](https://mlsanity.com/paper/2609.33738/) (2026)
- [Evaluating LLM Creativity through Long-Tail Performance](https://mlsanity.com/paper/2610.12998/) (2026)

## Abstract (arXiv)

Evaluating the creativity of large language models (LLMs) in story writing is difficult because LLM-generated stories could seemingly look creative but be very similar to some existing stories in their huge and proprietary training corpus. To overcome this challenge, we introduce a novel benchmark dataset with varying levels of prompt specificity: CS4 (Comparing the Skill of Creating Stories by Controlling the Synthesized Constraint Specificity). By increasing the number of requirements/constraints in the prompt, we can increase the prompt specificity and hinder LLMs from retelling high-quality narratives in their training data. Consequently, CS4 empowers us to indirectly measure the LLMs' creativity without human annotations. Our experiments on LLaMA, Gemma, and Mistral not only highlight the creativity challenges LLMs face when dealing with highly specific prompts but also reveal that different LLMs perform very differently under different numbers of constraints and achieve different balances between the model's instruction-following ability and narrative coherence. Additionally, our experiments on OLMo suggest that Learning from Human Feedback (LHF) can help LLMs select better stories from their training data but has limited influence in boosting LLMs' ability to produce creative stories that are unseen in the training corpora. The benchmark is released at https://github.com/anirudhlakkaraju/cs4benchmark.