# Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models

arXiv: https://arxiv.org/abs/2608.26161 · HTML: https://mlsanity.com/paper/2608.26161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 6 of 6)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments](https://mlsanity.com/paper/2406.00092/) (2024)
- [Enough Coin Flips Can Make LLMs Act Bayesian](https://mlsanity.com/paper/2503.04722/) (2025)
- [Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models](https://mlsanity.com/paper/2510.12080/) (2025)

## Abstract (arXiv)

Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and decision-making, high-fidelity probabilistic sampling remains a persistent challenge. When generating random variables, LLMs consistently exhibit systematic biases that warp the target probability distributions. Current approaches often rely on a single, self-generated seed, which inherits model-specific biases. To overcome this vulnerability, we introduce Dual-Seed Comparison (DSC), a transparent, tool-free protocol that utilizes two independent LLM-generated seeds to neutralize bias. DSC compares the character-level ordinal values of the two seeds to construct a bit sequence, converts and normalizes this sequence into a pseudo-uniform variate, and then maps the variate to the target distribution through the inverse cumulative distribution function (CDF). Empirical results show that DSC substantially outperforms existing methods across 96% of evaluated settings. Beyond direct sampling, task-adapted variants based on the DSC comparison operator improve distributional control in MCQ generation and attribute-constrained text-to-image prompting.