# Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

arXiv: https://arxiv.org/abs/2504.15266 · HTML: https://mlsanity.com/paper/2504.15266/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 103 of its 161 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 30 of 103)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)

## Built on by (most cited first, 29 of 29)

- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [Next-Latent Prediction Transformers Learn Compact World Models](https://mlsanity.com/paper/2511.05963/) (2025)
- [d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching](https://mlsanity.com/paper/2509.23094/) (2025)
- [Language Modeling with Hyperspherical Flows](https://mlsanity.com/paper/2605.11125/) (2026)
- [Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries](https://mlsanity.com/paper/2510.14751/) (2025)
- [On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity](https://mlsanity.com/paper/2606.26091/) (2026)
- [MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility](https://mlsanity.com/paper/2605.16616/) (2026)
- [Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling](https://mlsanity.com/paper/2509.01649/) (2025)
- [Measuring Combinatorial Creativity in Large Language Models and Humans](https://mlsanity.com/paper/2509.21043/) (2025)
- [Polychromic Objectives for Reinforcement Learning](https://mlsanity.com/paper/2509.25424/) (2025)
- [CREATE: Testing LLMs for Associative Creativity](https://mlsanity.com/paper/2603.09970/) (2026)
- [HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds](https://mlsanity.com/paper/2510.15614/) (2025)
- [Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization](https://mlsanity.com/paper/2601.21358/) (2026)
- [Free Lunch for Pass@k? Low Cost Diverse Sampling for Diffusion Language Models](https://mlsanity.com/paper/2603.04893/) (2026)
- [Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models](https://mlsanity.com/paper/2604.00375/) (2026)
- [Causal Autoregressive Diffusion Language Model](https://mlsanity.com/paper/2601.22031/) (2026)
- [Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models](https://mlsanity.com/paper/2601.22629/) (2026)
- [Internal Planning in Language Models: Characterizing Horizon and Branch Awareness](https://mlsanity.com/paper/2509.25260/) (2025)
- [Leveraging AI multimodal geospatial foundation models for improved near-real-time flood mapping at a global scale](https://mlsanity.com/paper/2512.02055/) (2025)
- [Multiple Token Divergence: Measuring and Steering In-Context Computation Density](https://mlsanity.com/paper/2512.22944/) (2025)
- [Hierarchical Latent Prediction for Language Models](https://mlsanity.com/paper/2608.05806/) (2026)
- [How to model Human Actions distribution with Event Sequence Data](https://mlsanity.com/paper/2510.05856/) (2025)
- [SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning](https://mlsanity.com/paper/2601.21649/) (2026)
- [Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors](https://mlsanity.com/paper/2603.14087/) (2026)
- [Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers](https://mlsanity.com/paper/2605.13450/) (2026)
- [BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers](https://mlsanity.com/paper/2606.02241/) (2026)
- [Sample What You Say: Aligning Language Models to Sample the Distributions They State](https://mlsanity.com/paper/2609.34929/) (2026)
- [Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems](https://mlsanity.com/paper/2609.38806/) (2026)
- [Evaluating LLM Creativity through Long-Tail Performance](https://mlsanity.com/paper/2610.12998/) (2026)

## Abstract (arXiv)

We design a suite of minimal algorithmic tasks that are a loose abstraction of open-ended real-world tasks. This allows us to cleanly and controllably quantify the creative limits of the present-day language model. Much like real-world tasks that require a creative, far-sighted leap of thought, our tasks require an implicit, open-ended stochastic planning step that either (a) discovers new connections in an abstract knowledge graph (like in wordplay, drawing analogies, or research) or (b) constructs new patterns (like in designing math problems or new proteins). In these tasks, we empirically and conceptually argue how next-token learning is myopic; multi-token approaches, namely teacherless training and diffusion models, comparatively excel in producing diverse and original output. Secondly, to elicit randomness without hurting coherence, we find that injecting noise at the input layer (dubbed seed-conditioning) works surprisingly as well as (and in some conditions, better than) temperature sampling from the output layer. Thus, our work offers a principled, minimal test-bed for analyzing open-ended creative skills, and offers new arguments for going beyond next-token learning and temperature sampling. We make part of the code available under https://github.com/chenwu98/algorithmic-creativity