Metraipolis › archive › dc_eebbe37d87bf

GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity — arXiv:2609.05284

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.05284
License (as archived): CC0-1.0
Archived: 2026-10-16T22:23:28.937Z
SHA-256 of the archived text: 842f6aec92e1689be0be26df52a851ec86a8b5f92cbd21041f1560d98ff98004
Stable URL of this page: https://metraipolis.com/documento/dc_eebbe37d87bf

How to cite

GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity — arXiv:2609.05284 — arXiv (en), https://arxiv.org/abs/2609.05284 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eebbe37d87bf (Metraipolis archive dc_eebbe37d87bf, sha256 842f6aec92e1689be0be26df52a851ec86a8b5f92cbd21041f1560d98ff98004)

BibTeX

@misc{dceebbe37d87bf,
  title = {GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity — arXiv:2609.05284},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05284},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eebbe37d87bf; sha256 842f6aec92e1689be0be26df52a851ec86a8b5f92cbd21041f1560d98ff98004},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05284. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs). However, the reasoning processes of LLMs often exhibit uncertainty, where LLMs often produce a proliferation of divergent branches at each reasoning step even when fed the same prompting inputs, and certain branches exhibit evidently incredible, even nonsensical, reasoning chains and results. In this paper, we propose the Graph-complexity-based UncerTainty (GUT) method for investigating the reasoning uncertainty of LLMs. The key idea of GUT is to characterize the potential branches of each reasoning chain with a directed acyclic graph, thereby ensuring that all potential branches are comprehensively covered within the graph space. Building upon this recognition, we further build two modules of GUT, that is, a Quantification (GUT-Q) module and an Optimization (GUT-O) module, for quantifying and reducing the reasoning uncertainty of LLMs, respectively. GUT-Q measures LLM reasoning uncertainty by approximating the reasoning space complexity with graph complexity. GUT-O implements uncertainty optimization by treating negative uncertainty as the reward function in reinforcement learning. Experimental results conducted on four LLMs and five datasets validate the effectiveness of GUT.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05284 — 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 2026-10-16T22:18:11.454Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).