相关论文: Contextual Linear Activation Steering of Language …

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

A fundamental challenge in autonomous driving is the integration of high-level, semantic reasoning for long-tail events with low-level, reactive control for robust driving. While large vision-language models (VLMs) trained on web-scale data…

Large Language Models (LLMs) have achieved remarkable capabilities, but their immense computational demands during training remain a critical bottleneck for widespread adoption. Low-rank training has received attention in recent years due…

Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with…

Large language models that require multiple GPU cards to host are usually the most capable models. It is necessary to understand and steer these models, but the current technologies do not support the interpretability and steering of these…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes in model activations,…

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical…

Data collection from manual labeling provides domain-specific and task-aligned supervision for data-driven approaches, and a critical mass of well-annotated resources is required to achieve reasonable performance in natural language…

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of…

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers…

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even…

Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token…

Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(static pruning or dynamic activation) address this partially,…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Deep neural networks (DNNs) have achieved remarkable success across domains but remain difficult to interpret, limiting their trustworthiness in high-stakes applications. This paper focuses on deep vision models, for which a dominant line…

Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022).…