相关论文: WilKE: Wise-Layer Knowledge Editor for Lifelong Kn…

Knowledge Editing (KE) has emerged as a promising paradigm for updating facts in Large Language Models (LLMs) without retraining. However, progress in Multilingual Knowledge Editing (MKE) is currently hindered by biased evaluation…

The important challenge of keeping knowledge in Large Language Models (LLMs) up-to-date has led to the development of various methods for incorporating new facts. However, existing methods for such knowledge editing still face difficulties…

Deep neural networks are becoming increasingly pervasive in academia and industry, matching and surpassing human performance on a wide variety of fields and related tasks. However, just as humans, even the largest artificial neural networks…

As real-world knowledge evolves, the information embedded within large language models (LLMs) can become outdated, inadequate, or erroneous. Model editing has emerged as a prominent approach for updating LLMs' knowledge with minimal…

As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static…

The widespread dissemination of fake news on social media has significantly impacted society, resulting in serious consequences. Conventional deep learning methodologies employing small language models (SLMs) suffer from extensive…

Large Language Models (LLMs) suffer from a critical limitation: their knowledge is static and quickly becomes outdated. Retraining these massive models is computationally prohibitive, while existing knowledge editing techniques can be slow…

Collaborative learning of large language models (LLMs) has emerged as a new paradigm for utilizing private data from different parties to guarantee efficiency and privacy. Meanwhile, Knowledge Editing (KE) for LLMs has also garnered…

Retrieval-augmented large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, addressing inherent challenges in knowledge update and factual inadequacy. However, inconsistencies between…

Word-level quality estimation (QE) methods aim to detect erroneous spans in machine translations, which can direct and facilitate human post-editing. While the accuracy of word-level QE systems has been assessed extensively, their usability…

Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge…

LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static…

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks, it becomes evident that these design choices lead to…

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters. Yet, LMs often generate the factually incorrect responses to the given queries, since their knowledge may be…

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the…

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a…

Large Language Models (LLMs) have emerged as a new information channel. Meanwhile, one critical but under-explored question is: Is it possible to bypass the safety alignment and inject harmful information into LLMs stealthily? In this…

Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing…