כתבה
arXiv cs.AI ·
GUT: חיסרון ואופטימיזציה של הברירת-מחדל של LLMs דרך רכיבת-גרף
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity
GUT - חיסרון ואופטימיזציה של הברירת-מחדל של LLMs דרך רכיבת-גרף. המאמר מציע פתרון לבעיית הברירת-מחדל של LLMs.
תקציר מקורי באנגליתarXiv:2609.05284v1 Announce Type: new Abstract: 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 upo
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית