相关论文: Benchmarking Safety Risks of Knowledge-Intensive R…
The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…
Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…
Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, while whether LLMs possess the capability to modify concepts…
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…
Knowledge editing aims at updating knowledge of large language models (LLMs) to prevent them from becoming outdated. Existing work edits LLMs at the level of factual knowledge triplets. However, natural knowledge updates in the real world…
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…
The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…
Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these…
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining…
The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…
Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or…
Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated…
While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…
The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…
Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…
Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods often struggle with complex tasks, such as multi-hop reasoning.…
Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in…
The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…