# Probabilistic Concept-Aware Steering for Trustworthy LLM Inference

arXiv: https://arxiv.org/abs/2607.18259 · HTML: https://mlsanity.com/paper/2607.18259/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 35 of its 45 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 30 of 35)

- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors](https://mlsanity.com/paper/2410.12299/) (2024)
- [Understanding LLMs: A Comprehensive Overview from Training to Inference](https://mlsanity.com/paper/2401.02038/) (2024)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning](https://mlsanity.com/paper/2312.17484/) (2023)
- [Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs](https://mlsanity.com/paper/2412.13337/) (2024)
- [Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering](https://mlsanity.com/paper/2410.16314/) (2024)
- [Towards Reliable Evaluation of Behavior Steering Interventions in LLMs](https://mlsanity.com/paper/2410.17245/) (2024)
- [Steering off Course: Reliability Challenges in Steering Language Models](https://mlsanity.com/paper/2504.04635/) (2025)
- [ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2407.21534/) (2024)
- [SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals](https://mlsanity.com/paper/2502.01042/) (2025)
- [Improved Representation Steering for Language Models](https://mlsanity.com/paper/2505.20809/) (2025)
- [SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity](https://mlsanity.com/paper/2401.17072/) (2024)
- [Contextualization Distillation from Large Language Model for Knowledge Graph Completion](https://mlsanity.com/paper/2402.01729/) (2024)
- [Differentially Private Steering for Large Language Model Alignment](https://mlsanity.com/paper/2501.18532/) (2025)
- [Current and Future Use of Large Language Models for Knowledge Work](https://mlsanity.com/paper/2503.16774/) (2025)
- [Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective](https://mlsanity.com/paper/2506.17930/) (2025)
- [COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics](https://mlsanity.com/paper/2603.06495/) (2026)
- [Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection](https://mlsanity.com/paper/2603.06745/) (2026)

## Abstract (arXiv)

Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to intermediate activations during inference. However, existing SV methods frequently yield representation-incoherent behaviors that undermine interpretability and fine-grained control, largely because prior work has focused on binary positive-negative steering evaluation while employing discrete clustering metrics that fail to capture the continuous spectrum of semantic alignment. In this work, we present the Probabilistic Concept-Aware Steering (PCS) framework for LLM inference. PCS preserves original task competence while providing controllable, safety-oriented semantic bias through concept-driven steering-vector retrieval and probabilistic strength calibration.