发现大模型内部存在概念吸引子，可直接操控实现翻译、去幻觉等任务。
Concept Attractors in LLMs and their Applications
- 用迭代函数系统解释模型层如何将相似语义映射到固定点
- 不训练直接操作吸引子，效果媲美甚至超过专用模型
- 适合需要快速部署且通用性强的场景，如安全防护与数据生成
大语言模型在特定层会将语义相关但形式差异大的提示映射到相似的内部表示，我们发现这种现象可用迭代函数系统（IFS）解释：各层作为收缩映射，将输入导向与概念相关的吸引子。基于此洞察，我们提出无需训练的简单干预方法，直接作用于这些吸引子，成功应用于语言翻译、幻觉抑制、安全防护及合成数据生成等任务。尽管方法简洁，其性能仍可比肩或超越专用基线，在基线表现不佳时尤其突出，为替代繁重微调提供高效且可泛化的方案。
原文摘要 · Abstract (English)
Large language models (LLMs) often map semantically related prompts to similar internal representations at specific layers, even when their surface forms differ widely. We show that this behavior can be explained through Iterated Function Systems (IFS), where layers act as contractive mappings toward concept-specific Attractors. We leverage this insight and develop simple, training-free methods that operate directly on these Attractors to solve a wide range of practical tasks, including language translation, hallucination reduction, guardrailing, and synthetic data generation. Despite their simplicity, these Attractor-based interventions match or exceed specialized baselines, offering an efficient alternative to heavy fine-tuning, generalizable in scenarios where baselines underperform.
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。