迈向对大语言模型微调中记忆化知识无法泛化的机制性理解

摘要

微调大语言模型以注入新知识面临一个关键挑战：模型能快速记忆新事实，却无法将其应用于下游推理任务。我们将这种失败形式化为**知用鸿沟**，其特点表现为准确率差距以及记忆与泛化之间的时间延迟。为理解这一现象，我们使用未知知识微调大语言模型，并采用一种名为"自修补"的新型干预技术，监测知识在模型内部的空间渗透动态。自修补能识别出通过重新定位表征可显著改善失败泛化案例的激活位置。这些结果与知识回路失调假说一致：记忆的表征可能存在于模型内部，但未被路由至计算有效的层。为验证这一诊断发现的实用性，我们设计了一种简单启发式策略，该策略可恢复58%-75%的理论优化空间，用于解决泛化失败问题。跨领域实验验证了该发现的稳健性。

English

Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks. We formalize this failure as the \textbf{Knowing--Using Gap}, characterized by an accuracy gap and a temporal lag between memorization and generalization. To understand this phenomenon, we fine-tune LLMs with unseen knowledge and monitor the spatial permeation dynamics of the knowledge internally using a novel intervention technique called self-patching. Self-patching identifies activation locations where relocating representations substantially improves failed generalization cases. These results are consistent with a knowledge-circuit misalignment hypothesis: memorized representations can exist internally but may not be routed to computation-effective layers. To demonstrate the practicality of this diagnostic finding, we design a simple heuristic strategy which recovers 58--75\% of the oracle headroom in generalization failure. Experiments are done cross-domain for the robustness of this finding.