EMNLP Findings2025
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrieval
Jaehyung Seo, Dahyun Jung, Jaewook Lee, Yongchan Chun, Dongjun Kim, Hwijung Ryu, Donghoon Shin, Heuiseok Lim
Abstract
Korean legal knowledge is subject to frequent temporal updates driven by societal needs and government policies. Even minor modifications to legal provisions can have significant consequences, yet continuously retraining large language models (LLMs) to incorporate such updates is resource-intensive and impractical. To address this, we propose KoLEG, an on-thefly Korean legal knowledge editing framework enhanced with continuous retrieval. KoLEG employs an Editing-Aware Learning Strategy and a LawEdit Retriever, which together adaptively integrate subtle linguistic nuances and continuous legislative amendments. To support this task, we construct the Korean Legislative Amendment Dataset, explicitly designed for continuous legal knowledge updates with attention to both temporal dynamics and linguistic subtleties. KoLEG outperforms existing locatethen-edit and retrieval-based editing methods, demonstrating superior effectiveness in legal knowledge editing while preserving linguistic capabilities. KoLEG maintains robust performance in sequential editing, improves performance on precedent application tasks, and is qualitatively validated by legal experts. The code is available at KoLEG Github.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites LoRA: Low-Rank Adaptation of Large Language Models
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites Locating and Editing Factual Associations in GPT
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites Fast Model Editing at Scale
- Locating and Editing Factual Associations in GPT cites Fast Model Editing at Scale
- Fast Model Editing at Scale cites LoRA: Low-Rank Adaptation of Large Language Models
Builds on14
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationJianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo et al.ACL Findings 2024 · 762 citations
- Fast Model Editing at ScaleEric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn et al.ICLR 2022 · 527 citations
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value AdaptorsTom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim et al.NeurIPS 2023 · 349 citations
Related papers
- Retrieval-Augmented Multilingual Knowledge EditingWeixuan Wang, Barry Haddow, Alexandra BirchACL 2024
- Improving Sequential Model Editing with Fact RetrievalXiaoqi Han, Ru Li, Hongye Tan, Yuanlong Wang et al.EMNLP Findings 2023 · 2 citations
- Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model EditingBhiman Kumar Baghel, Emma Jordan, Zheyuan Ryan Shi, Xiang Lorraine LiEMNLP Findings 2025 · 1 citation
- Towards Scalable Lifelong Knowledge Editing with Selective Knowledge SuppressionDahyun Jung, Jaewook Lee, Heuiseok LimACL 2026
- AdaEdit: Advancing Continuous Knowledge Editing For Large Language ModelsQi Li, Xiaowen ChuACL 2025
