Editing large language models: Problems, methods, and opportunities

Y Yao, P Wang, B Tian, S Cheng, Z Li, S Deng… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Despite the ability to train capable LLMs, the methodology for maintaining their relevancy
and rectifying errors remains elusive. To this end, the past few years have witnessed a surge …

Large knowledge model: Perspectives and challenges

H Chen - arxiv preprint arxiv:2312.02706, 2023‏ - arxiv.org
Humankind's understanding of the world is fundamentally linked to our perception and
cognition, with\emph {human languages} serving as one of the major carriers of\emph {world …

Larimar: Large language models with episodic memory control

P Das, S Chaudhury, E Nelson, I Melnyk… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is
one of the most pressing research challenges today. This paper presents Larimar-a novel …

Instructedit: Instruction-based knowledge editing for large language models

N Zhang, B Tian, S Cheng, X Liang, Y Hu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Knowledge editing for large language models can offer an efficient solution to alter a
model's behavior without negatively impacting the overall performance. However, the …

Configurable foundation models: Building llms from a modular perspective

C **ao, Z Zhang, C Song, D Jiang, F Yao, X Han… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Advancements in LLMs have recently unveiled challenges tied to computational efficiency
and continual scalability due to their requirements of huge parameters, making the …

College: Concept embedding generation for large language models

R Teehan, B Lake, M Ren - arxiv preprint arxiv:2403.15362, 2024‏ - arxiv.org
Current language models are unable to quickly learn new concepts on the fly, often
requiring a more involved finetuning process to learn robustly. Prompting in-context is not …

Perturbation-restrained sequential model editing

JY Ma, H Wang, HX Xu, ZH Ling, JC Gu - arxiv preprint arxiv:2405.16821, 2024‏ - arxiv.org
Model editing is an emerging field that focuses on updating the knowledge embedded within
large language models (LLMs) without extensive retraining. However, current model editing …

Editing Personality for Large Language Models

S Mao, X Wang, M Wang, Y Jiang, P **e… - … Conference on Natural …, 2024‏ - Springer
This paper introduces an innovative task focused on editing the personality traits of Large
Language Models (LLMs). This task seeks to adjust the models' responses to opinion …

ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

Y Park, C Yoon, J Park, D Lee, M Jeong… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large language models (LLMs) have significantly impacted many aspects of our lives.
However, assessing and ensuring their chronological knowledge remains challenging …

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

T Liu, Z Dong, L Zhang, H Wang, J Gao - arxiv preprint arxiv:2502.00602, 2025‏ - arxiv.org
Large language models (LLMs) have achieved remarkable performance on various natural
language tasks. However, they are trained on static corpora and their knowledge can …