用语言哲学破解大模型幻觉，提出可解释的缓解框架
From "Hallucination" to "Suture": Insights from Language Philosophy to Enhance Large Language Models
- 基于拉康符号链与缝合点理论，构建锚定式RAG框架
- 显著降低幻觉率，同时提升生成质量与模型性能
- 适合关注模型可解释性与理论基础的研究者
本文从语言哲学与精神分析视角审视大语言模型（LLMs）中的幻觉现象。通过引入拉康的“符号链”与“缝合点”概念，提出新型锚定式RAG（Anchor-RAG）框架，以应对主流方法依赖试错、公式调优或资源密集型训练的问题。该框架回归语言学根本原理，从理论上剖析幻觉成因，推导出兼具有效性与可解释性的算法与模型。实验表明，该方法不仅显著减少幻觉，还提升了输出质量与模型表现。本文旨在建立理解大模型幻觉的系统性理论框架，挑战当前领域内“试错-迭代”的研究范式，推动可解释性大模型的发展。
原文摘要 · Abstract (English)
This paper explores hallucination phenomena in large language models (LLMs) through the lens of language philosophy and psychoanalysis. By incorporating Lacan's concepts of the "chain of signifiers" and "suture points," we propose the Anchor-RAG framework as a novel approach to mitigate hallucinations. In contrast to the predominant reliance on trial-and-error experiments, constant adjustments of mathematical formulas, or resource-intensive methods that emphasize quantity over quality, our approach returns to the fundamental principles of linguistics to analyze the root causes of hallucinations in LLMs. Drawing from robust theoretical foundations, we derive algorithms and models that are not only effective in reducing hallucinations but also enhance LLM performance and improve output quality. This paper seeks to establish a comprehensive theoretical framework for understanding hallucinations in LLMs and aims to challenge the prevalent "guess-and-test" approach and rat race mentality in the field. We aspire to pave the way for a new era of interpretable LLMs, offering deeper insights into the inner workings of language-based AI systems.
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。