Research
Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that sol…
Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that solves this by having the model generate and manipulate a rando
Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that solves this by having the model generate and manipulate a random string. To be presented at #ICLR2026 this week! Blog: https://pub.sakana.ai/ssot Can LLMs flip coins in their heads? When prompted to “Flip a fair coin” 100 times, the heads to tails ratio drifts far from 50:50. LLMs can understand what the target probability should be, but generating outputs that faithfully follow a given distribution is a separate problem. …
Related
- String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation https://arxiv.org/abs/2510.21150 https://pub.sakana.…
- $S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
- TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
- GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
Source: David Ha (X) | 2026-04-20