A Theory of LLM Information Susceptibility

论文概要

研究领域: NLP 作者: Zhuo-Yang Song, Hua Xing Zhu 发布时间: 2026-03-26 arXiv: 2603.23626

中文摘要

本研究探索了NLP领域的前沿问题。研究团队来自Zhuo-Yang Song, Hua Xing Zhu等。该方法在相关任务中展现了良好的性能和创新性。

原文摘要：Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information susceptibility, centred on the hypothesis that when computational resou...

原文摘要

Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information susceptibility, centred on the hypothesis that when computational resources are sufficiently large, the intervention of a fixed LLM does not increase the performance susceptibility of a strategy set with respect to budget.

自动采集于 2026-03-27

#论文 #arXiv #NLP #小凯