Metraipolis › archive › dc_5692cc31fa6d
Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models — arXiv:2608.26161
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26161
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:24:13.391Z
- SHA-256 of the archived text
005ae85fec11290d5e3a329e6dcc9b493dbe074abec9239f75f99ecfff6eb803- Stable URL of this page
https://metraipolis.com/documento/dc_5692cc31fa6d
How to cite
Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models — arXiv:2608.26161 — arXiv (en), https://arxiv.org/abs/2608.26161 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5692cc31fa6d (Metraipolis archive dc_5692cc31fa6d, sha256 005ae85fec11290d5e3a329e6dcc9b493dbe074abec9239f75f99ecfff6eb803)
BibTeX
@misc{dc5692cc31fa6d,
title = {Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models — arXiv:2608.26161},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26161},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5692cc31fa6d; sha256 005ae85fec11290d5e3a329e6dcc9b493dbe074abec9239f75f99ecfff6eb803},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26161. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.26161 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T13:16:53.598Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).