Related papers: Spherical Steering: Geometry-Aware Activation Rota…
Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…
Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…
Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown that LLMs often…
Large language models (LLMs) have recently shown strong performance as zero-shot rankers, yet their effectiveness is highly sensitive to prompt formulation, particularly role-play instructions. Prior analyses suggest that role-related…
Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…
Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…
Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…
Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts,…
The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…
Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce…
Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypotheses a priori by modifying architectural topology to observe training dynamics. We study…
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge, and harmful…
Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document…
Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great promise for achieving general-purpose robotic systems. Despite…
Measurement of task progress through explicit, actionable milestones is critical for robust robotic manipulation. This progress awareness enables a model to ground its current task status, anticipate verifiable intermediate states, and…
This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…
Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…
Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…
Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…
A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…