arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2509.25593cs.AIcs.CLcs.HCcs.IR

使用 LLM 智能体因果性地类自动编码器生成反馈模糊认知图

Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent

  • Department of Electrical and Computer Engineering(电气与计算机工程系)
  • University of Southern California(南加州大学)
  • School of Computing and Information Sciences(计算与信息科学学院)
  • Florida International University(佛罗里达国际大学)

机构由 AI 辅助整理,请以论文原文为准。

Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko

更新

AI总结:

提出一种由 LLM 智能体实现的类自动编码器可解释框架,将反馈 FCM 编码为自然文本并重建,通过系统指令近似恒等映射且保留强因果边。

AI中文摘要:

大型语言模型(LLM)能够将反馈因果模糊认知图(FCM)映射为文本,随后再从该文本重建 FCM。这一可解释 AI 系统近似实现了从 FCM 到其自身的恒等映射,其运作方式类似于自动编码器(AE)。与黑箱 AE 不同,编码器和解码器都会解释各自的决策。与 AE 中的隐变量和突触网络不同,人类能够阅读并解释编码后的文本。该 LLM 智能体通过一系列系统指令来近似恒等映射,且不会将输出与输入进行比较。重建是有损的,因为它会移除较弱的因果边或规则,同时保留较强的因果边。即使编码器为使文本听起来更自然而权衡了有关 FCM 的某些细节,它仍会保留较强的因果边。

英文摘要:

A large language model (LLM) can map a feedback causal fuzzy cognitive map (FCM) into text and then reconstruct the FCM from the text. This explainable AI system approximates an identity map from the FCM to itself and resembles the operation of an autoencoder (AE). Both the encoder and the decoder explain their decisions in contrast to black-box AEs. Humans can read and interpret the encoded text in contrast to the hidden variables and synaptic webs in AEs. The LLM agent approximates the identity map through a sequence of system instructions that does not compare the output to the input. The reconstruction is lossy because it removes weak causal edges or rules while it preserves strong causal edges. The encoder preserves the strong causal edges even when it trades off some details about the FCM to make the text sound more natural.

补充信息

↑