让大模型在推理时自动选择通用或记忆模式，提升可靠性。
Generalization or Memorization: Dynamic Decoding for Mode Steering
- 基于信息瓶颈理论，区分通用推理与记忆复现
- 动态识别并引导模型走向更可靠的通用路径
- 适合追求高可信度的复杂推理场景
大型语言模型（LLMs）表现出令人担忧的双重特性：既能实现卓越的泛化，又会僵化地复现训练数据。这种不可预测性损害了其在高风险应用中的可靠性。本文提出统一框架，用于理解、识别并控制这两种不同推理模式。首先，基于信息瓶颈（Information Bottleneck, IB）原理，将泛化建模为学习压缩的、任务相关的表征，而记忆则被视为压缩失败。在此理论基础上，我们开发了动态模式转向（Dynamic Mode Steering, DMS）——一种新型推理时算法，包含两个组件：(1) 轻量级、因果驱动的线性探测器，实时识别模型对记忆的依赖程度；(2) 动态激活转向机制，引导模型计算向预识别的泛化电路倾斜。我们将DMS视为一种自适应的自对比解码形式。在推理与忠实性任务上的实验表明，DMS显著提升了逻辑一致性和事实准确性，为增强LLM可靠性提供了原则性方法。
原文摘要 · Abstract (English)
Large Language Models (LLMs) exhibit a troubling duality, capable of both remarkable generalization and brittle, verbatim memorization of their training data. This unpredictability undermines their reliability in high-stakes applications. In this work, we propose a unified framework to understand, identify, and control these distinct reasoning modes. First, we introduce a theoretical model based on the Information Bottleneck (IB) principle, formalizing generalization as the learning of a compressed, task-relevant representation and memorization as a failure to compress. Building on this theory, we develop Dynamic Mode Steering (DMS), a novel inference-time algorithm which comprises two components: (1) a lightweight, causally-grounded linear probe that identifies the model's instantaneous reliance on memorization, and (2) a dynamic activation steering mechanism that nudges the model's computation towards pre-identified generalization circuits. We frame DMS as a form of adaptive, self-contrastive decoding. Experiments on reasoning and faithfulness tasks demonstrate that DMS significantly improves logical consistency and factual accuracy, thereby offering a principled approach to enhancing LLM reliability.
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。