Inference-time steering provides a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying model activations without updating weights. However, existing methods often rely on a global intervention vector, overlook token-level causal influence, and underutilize model logits, especially in multimodal settings where visual and textual inputs contribute unevenly. We propose GrAInS, a contrastive, gradient-based approach that leverages Integrated Gradients to identify top-k influential tokens and construct directional steering vectors based on their contribution to preferred over dispreferred outputs. These vectors guide activation intervention at each layer, preserving the representational scale. GrAInS outperforms fine-tuning and prior steering methods on both LLM and VLM tasks: improving TruthfulQA accuracy by 13.22% (Llama-3.1-8B), reducing MMHal-Bench hallucinations from 0.624 to 0.514 (LLaVA-1.6-7B), and increasing SPA-VL alignment by 8.11%, all without degrading fluency or general capabilities.

Language models, while capable of generating remarkably coherent and seemingly accurate text, can occasionally produce undesirable content including harmful or toxic outputs. In this paper, we present a new two-stage approach to detect and mitigate undesirable content generations by rectifying activations. First, we train an ensemble of layerwise classifiers to detect undesirable content using activations by minimizing a smooth surrogate of the risk-aware score. Then, for detected undesirable contents, we propose layerwise distributional steering policies that transform the attention heads. These policies are computed through principled semidefinite programming aims to minimally perturb the attention distribution while probabilistically guaranteeing the effectiveness of the editions. Empirical evaluations across multiple language models and datasets show that our method outperforms baselines in reducing the generation of undesirable output.

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 the LLM’s parameters. However, existing ITI approaches fail to scale to multi-attribute settings with conflicts, such as enhancing helpfulness while also reducing toxicity. To address this, we introduce Multi-Attribute Targeted Steering (MAT-Steer), a novel steering framework designed for selective token-level intervention across multiple attributes. We achieve this by learning steering vectors using an alignment objective that shifts the model’s internal representations of undesirable outputs closer to those of desirable ones while enforcing sparsity and orthogonality among vectors for different attributes, thereby reducing inter-attribute conflicts. We evaluate MAT-Steer in two distinct settings: (i) on question answering (QA) tasks where we balance attributes like truthfulness, bias, and toxicity; (ii) on generative tasks where we simultaneously improve attributes like helpfulness, correctness, and coherence. MAT-Steer outperforms existing ITI and parameter-efficient fine-tuning approaches across both task types (e.g., average 3% accuracy gain across QA tasks and 55.82% win rate against the best ITI baseline).