Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression

About

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model's original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.

Dahyun Jung, Jaewook Lee, Heuiseok Lim• 2026

Related benchmarks

TaskDatasetResultRank
Knowledge EditingzsRE
Generality0.9483
268
Model EditingRIPE
Reliability99.42
50
Knowledge EditingCounterFact
AVG Score92.96
20
Knowledge EditingUniEdit
Average Score91.65
9
Showing 4 of 4 rows

Other info

Follow for update