让大模型的指令与参数互相转换，揭示其内在关联。
Shuttle Between the Instructions and the Parameters of Large Language Models
- 构建神经网络框架SHIP，实现指令与参数间的双向映射。
- 在推理任务中，诱导能力显著优于现有方法。
- 适合研究模型内部机制与指令设计的学者使用。
通过指令与大型语言模型（LLMs）的交互已广泛研究。本文注意到，指令和模型参数都是任务数据的压缩形式，二者可能存在强相关性，可相互预测。为此，提出新型神经网络框架SHIP（Shuttle Between the Instructions and the Parameters），用于建模和学习指令与大模型参数之间的双向映射关系。在指令推导与归纳任务上验证了该方法的有效性：SHIP在推导能力上优于基线方法，而在归纳能力上则显著超越。此外，通过结合双向映射过程，SHIP展现出出色的归纳推理性能。代码与数据已公开于 https://anonymous.4open.science/r/Shuttle-Between-Instructions-Parameters/。
原文摘要 · Abstract (English)
The interaction with Large Language Models (LLMs) through instructions has been extensively investigated in the research community. While instructions have been widely used as the guidelines for task solving, this paper further notices that both instructions and parameters are the compression of task data. Therefore, they could be strongly correlated and can be learned to predict one from the other. This paper proposes a novel neural network framework, SHIP (\textbf{Sh}uttle between the \textbf{I}nstructions and the \textbf{P}arameters), to model and learn the mutual mappings between the instructions and the parameters of LLMs. We verify that SHIP can effectively map one of the instructions/parameters to the other by evaluating it on the tasks of instruction deduction and induction. The results show that SHIP performs better than existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities. Moreover, SHIP can effectively combine the two mapping processes to perform excellent inductive reasoning. The code and data for this paper are released at https://anonymous.4open.science/r/Shuttle-Between-Instructions-Parameters/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。