相关论文: Norm Growth and Stability Challenges in Localized …

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for…

Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specific knowledge within LLMs. However, training-based approaches…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and…

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and…

Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real…

Sequential knowledge editing techniques aim to continuously update knowledge in large language models at low cost, preventing models from generating outdated or incorrect information. However, existing sequential editing methods suffer from…

Existing methods in Multimodal Knowledge Editing (MKE) have advanced the ability to correct outdated or inaccurate knowledge in Multimodal Large Language Models (MLLMs). However, they exhibit a critical limitation: while effectively…

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Large language models (LLMs) struggle with maintaining accurate knowledge due to conflicting/outdated parametric memories. While locate-and-edit methods address this, their reliance on models' internal representations leads to robustness…

Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two…

Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

In the evolving landscape of conversational AI, generating concise, context-aware, and human-like dialogue using small and medium-sized language models (LLMs) remains a complex challenge. This study investigates the influence of LoRA rank,…

Large language models (LLMs) have recently transformed both the academic and industrial landscapes due to their remarkable capacity to understand, analyze, and generate texts based on their vast knowledge and reasoning ability.…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing methods (KEs) that can change specific facts in LLMs with limited…

Sequential Locate-and-Edit (L&E) model editing can fail abruptly after many edits. We identify and formalize this failure as a positive norm-feedback loop, in which solved value vectors and edited MLP weights progressively amplify each…

Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs demonstrate remarkable versatility, MLLMs appears limited…