相关论文: EasyEdit2: An Easy-to-use Steering Framework for E…

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically…

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new…

Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by…

Agents based on Large Language Models (LLMs) have demonstrated strong capabilities across a wide range of tasks. However, deploying LLM-based agents in high-stakes domains comes with significant safety and ethical risks. Unethical behavior…

Model editing aims to efficiently update a pre-trained model's knowledge without the need for time-consuming full retraining. While existing pioneering editing methods achieve promising results, they primarily focus on editing single-modal…

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…

The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the…

Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse formats, such as…

We present a training-free framework for continuous and controllable image editing at test time for text-conditioned generative models. In contrast to prior approaches that rely on additional training or manual user intervention, we find…

Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability…

While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a…

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Large Language Models (LLMs) are widely deployed in downstream tasks, but keeping their knowledge up-to-date via retraining or fine-tuning is often computationally expensive. Model editing provides a more efficient alternative by updating a…