相关论文: Global Evolutionary Steering: Refining Activation …

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,…

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…

Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven by empirical insights and lack theoretical performance…

Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-standard architectures from scratch remains costly and risky.…

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

We present Fusion Steering, an activation steering methodology that improves factual accuracy in large language models (LLMs) for question-answering (QA) tasks. This approach introduces flexible steering configurations, including full-layer…

As they become increasingly multilingual, Large Language Models (LLMs) exhibit more language confusion, i.e., they tend to generate answers in a language different from the language of the prompt or the answer language explicitly requested…

Augmenting large language models (LLM) to use external tools enhances their performance across a variety of tasks. However, prior works over-rely on task-specific demonstration of tool use that limits their generalizability and…

Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system…

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…

Optimization can be found in many real-life applications. Designing an effective algorithm for a specific optimization problem typically requires a tedious amount of effort from human experts with domain knowledge and algorithm design…

Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches…

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…