From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an adversarial elicitation perspective, revealing that edited knowledge is often not fully erased and continues to surface, with consistent failures observed across diverse model architectures. To explain this behavior, we conduct a mechanistic analysis of popular KE methods. We show that low-rank updates do not overwrite existing knowledge but instead redistribute it within the model's representation space. Furthermore, we find that these methods act as targeted suppression mechanisms that reduce the likelihood of expressing original facts, rather than removing them from the model. Analysis of the loss landscape reveals that edited knowledge lies in narrow, anisotropic regions that are highly sensitive to perturbations, making them highly vulnerable to indirect prompting and adversarial attacks. By exposing these profound architectural vulnerabilities, our work proves that KE algorithms are inherently bypassable and motivates a fundamental reevaluation of how we deploy post-hoc updates in several LLM applications.

Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates knowledge editing (KE), which updates specific knowledge in an LLM without changing unrelated others. Recent works move from structured knowledge triples toward unstructured KE (UKE), where the edit is a free-form passage that may state multiple facts at once. Nonetheless, existing editors inject such a passage yet fail to use it: the edited model can recall the passage, but can neither answer atomic questions about its facts nor compose them into multi-hop reasoning. We attribute this missing property, which we term composability, to editors' passive reliance on the fixed passage as the sole learning source. In response, we cast editing as a proactive self-distillation from a privileged in-context state of the same model, which requires no external supervision. We further reveal that due to the novelty of the injected knowledge, the pre-edited model's own rollouts rarely cover it, which limits the effectiveness of pure on-policy distillation. To close this gap, we propose HPSE, which builds a hybrid rollout that steps in to place missing facts onto the student's own trajectory precisely where its coverage fails, while staying on-policy elsewhere. We theoretically analyze HPSE's advantage over pure on-policy distillation, and empirically establish its plug-and-play improvements across four LLM backbones and two KE editors under various scenarios.

Large Language Models (LLMs) are increasingly deployed in real-world applications that require access to up-to-date knowledge. However, retraining LLMs is computationally expensive. Therefore, knowledge editing techniques are crucial for maintaining current information and correcting erroneous assertions within pre-trained models. Current benchmarks for knowledge editing primarily focus on recalling edited facts, often neglecting their logical consequences. To address this limitation, we introduce a new benchmark designed to evaluate how knowledge editing methods handle the logical consequences of a single fact edit. Our benchmark extracts relevant logical rules from a knowledge graph for a given edit. Then, it generates multi-hop questions based on these rules to assess the impact on logical consequences. Our findings indicate that while existing knowledge editing approaches can accurately insert direct assertions into LLMs, they frequently fail to inject entailed knowledge. Specifically, experiments with popular methods like ROME and FT reveal a substantial performance gap, up to 24%, between evaluations on directly edited knowledge and on entailed knowledge. This highlights the critical need for semantics-aware evaluation frameworks in knowledge editing.