用符号压缩提升大模型效率，让代码生成更省 token 还更易懂。
Enhancing Large Language Model Efficiencyvia Symbolic Compression: A Formal Approach Towards Interpretability
- 通过组合逻辑与信息论设计符号压缩框架，提升编码效率。
- 代码生成任务中实现 78.3% 的 token 压缩率，逻辑可追溯性提升 62%。
- 适合关注模型效率与可解释性的研究者和工程应用开发者。
大语言模型在代码生成与逻辑推理任务中面临严重的令牌效率瓶颈，直接影响推理成本与模型可解释性。本文提出一种基于符号压缩的正式框架，融合组合逻辑、信息论最优编码与上下文感知推理技术，实现令牌效率的质变提升，同时保持语义完整性。我们在函数式编程范式下建立数学框架，推导出符号密度与模型可解释性的定量关系，并提出可微分的压缩因子度量以评估编码效率。此外，利用参数高效微调（PEFT）技术实现对 GAEL 语言的低成本应用。实验表明，该方法在代码生成任务中实现 78.3% 的令牌压缩率，通过结构显式使逻辑可追溯性提升 62%。本研究为大模型高效推理提供了新的理论工具，并开辟了模型可解释性研究的符号路径。
原文摘要 · Abstract (English)
Large language models (LLMs) face significant token efficiency bottlenecks in code generation and logical reasoning tasks, a challenge that directly impacts inference cost and model interpretability. This paper proposes a formal framework based on symbolic compression,integrating combinatory logic, information-theoretic optimal encoding, and context-aware inference techniques to achieve a step-change improvement in token efficiency while preserving semantic integrity. We establish a mathematical framework within a functional programming paradigm, derive the quantitative relationship between symbolic density and model interpretability, and propose a differentiable compression factor metric to evaluate encoding efficiency. Furthermore, we leverage parameter-efficient fine-tuning (PEFT) techniques to achieve a low-cost application of the GAEL language. Experimental results show that this method achieves a 78.3% token compression rate in code generation tasks while improving logical traceability by 62% through structural explicitness. This research provides new theoretical tools for efficient inference in LLMs and opens a symbolic path for modelinterpretability research.
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。