相关论文: Efficiently Quantifying and Mitigating Ripple Effe…

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information,…

Mixed effects (ME) models inform a vast array of problems in the physical and social sciences, and are pervasive in meta-analysis. We consider ME models where the random effects component is linear. We then develop an efficient approach for…

This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to…

Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal research area. While these…

Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effective in mitigating such behaviours on top of the existing…

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…

Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image source method (ISM) can efficiently generate early…

Diffusion models have demonstrated impressive performance in text-guided image generation. Current methods that leverage the knowledge of these models for image editing either fine-tune them using the input image (e.g., Imagic) or…

Evaluations of model editing currently only use the `next few token' completions after a prompt. As a result, the impact of these methods on longer natural language generation is largely unknown. We introduce long-form evaluation of model…

Although recent years have witnessed significant advancements in image editing thanks to the remarkable progress of text-to-image diffusion models, the problem of non-rigid image editing still presents its complexities and challenges.…

Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we introduce SMILE…

We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic…

Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM…

The current trend toward ever-larger models makes standard retraining procedures an ever-more expensive burden. For this reason, there is growing interest in model editing, which enables computationally inexpensive, interpretable, post-hoc…

Not a day goes by without hearing about the impressive feats of large language models (LLMs), and equally, not a day passes without hearing about their challenges. LLMs are notoriously vulnerable to biases in their dataset, leading to…

The popularity and widespread use of pruning and quantization is driven by the severe resource constraints of deploying deep neural networks to environments with strict latency, memory and energy requirements. These techniques achieve high…

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter perturbations to a static…

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…