Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
Summary
This paper proposes using steering vectors for control over language model behavior and latent space-based calibrators to assess trustworthiness, aiming to demystify internal representations and build more reliable AI systems.
View Cached Full Text
Cached at: 07/02/26, 05:35 AM
# Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust Source: [https://arxiv.org/abs/2607.00083](https://arxiv.org/abs/2607.00083) [View PDF](https://arxiv.org/pdf/2607.00083) > Abstract:Language models have changed from unreliable text generators to highly\-capable large models with trillions of parameters\. Capability increases come hand\-in\-hand with increases in scale, making understanding the internal representations of models more challenging\. Since millions of users increasing rely on language models to interact with external tools or make decisions in medium or high\-stakes scenarios, we need to establish control over model behavior and know when to trust model outputs\. In this paper, we discuss our contributions on harnessing the latent spaces by proposing steering vectors for control and developing latent space\-based model calibrators for trust\. Together, our contributions help demystify the latent spaces of language models and offer new insights into how to harness model internals to build more trustworthy language technology\. ## Submission history From: Nishant Subramani \[[view email](https://arxiv.org/show-email/f2d39a71/2607.00083)\] **\[v1\]**Tue, 30 Jun 2026 19:21:46 UTC \(14,778 KB\)
Similar Articles
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Introduces Latent Reward Steering (Lrs), an adaptive inference-time framework that uses sparse autoencoder latent states and a learned reward model to implicitly promote cognitive behaviors like verification and backtracking in reasoning LLMs, improving performance across multiple models and benchmarks.
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
FineSteer is a novel inference-time steering framework that decomposes steering into conditional steering and fine-grained vector synthesis stages, using Subspace-guided Conditional Steering (SCS) and Mixture-of-Steering-Experts (MoSE) mechanisms to improve safety and truthfulness while preserving model utility. Experiments show 7.6% improvement over state-of-the-art methods on TruthfulQA with minimal utility loss.
Cultural Value Alignment Via Latent Activation Steering in Large Language Models
A framework for evaluating and steering cultural values in LLMs using scenario-based behavioral probing and activation steering, revealing latent entanglement of value dimensions.
Controlling Tool Use with Heading-Specific Activation Steering
This paper investigates whether tool-use decisions in large language models have stable internal representations that can be extracted and manipulated via activation steering, demonstrating that heading-specific steering vectors can suppress unnecessary tool use across five open-source models and three domains. The geometric analysis reveals that tool-invocation steps exhibit diffuse, bimodal alignment rather than the clean linear structure expected for parametrically grounded concepts.
CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
The paper introduces CALIBER, a method for calibrating confidence in reasoning language models by eliciting confidence estimates both before and after reasoning, with supervision targets matched to the information state. It achieves significant reductions in Expected Calibration Error (up to 52.5%) and strong Brier scores and AUROC across multiple benchmarks.