# Internal Value Alignment in Large Language Models through Controlled Value Vector Activation

arXiv: https://arxiv.org/abs/2507.11316 · HTML: https://mlsanity.com/paper/2507.11316/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 29 of 29)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [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)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Emergent Linear Representations in World Models of Self-Supervised Sequence Models](https://mlsanity.com/paper/2309.00941/) (2023)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP](https://mlsanity.com/paper/2210.10683/) (2022)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values](https://mlsanity.com/paper/2311.10766/) (2023)
- [Controlling Large Language Models Through Concept Activation Vectors](https://mlsanity.com/paper/2501.05764/) (2025)
- [Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning](https://mlsanity.com/paper/2310.11053/) (2023)
- [Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?](https://mlsanity.com/paper/2402.18120/) (2024)
- [CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses](https://mlsanity.com/paper/2407.10725/) (2024)
- [High-Dimension Human Value Representation in Large Language Models](https://mlsanity.com/paper/2404.07900/) (2024)
- [Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models](https://mlsanity.com/paper/2305.08625/) (2023)

## Built on by (most cited first, 16 of 16)

- [Steering LLMs for Culturally Localized Generation](https://mlsanity.com/paper/2603.23301/) (2026)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Controllable Value Alignment in Large Language Models through Neuron-Level Editing](https://mlsanity.com/paper/2602.07356/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Labels have Human Values: Value Calibration of Subjective Tasks](https://mlsanity.com/paper/2601.06631/) (2026)
- [VISPA: Pluralistic Alignment via Automatic Value Selection and Activation](https://mlsanity.com/paper/2601.12758/) (2026)
- [Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads](https://mlsanity.com/paper/2603.05772/) (2026)
- [Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph](https://mlsanity.com/paper/2603.15527/) (2026)
- [Constitutional Value Potentials: reading and steering internal priority margins in language models](https://mlsanity.com/paper/2606.15420/) (2026)
- [When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems](https://mlsanity.com/paper/2607.06807/) (2026)
- [What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces](https://mlsanity.com/paper/2608.22985/) (2026)
- [Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment](https://mlsanity.com/paper/2609.05800/) (2026)
- [Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values](https://mlsanity.com/paper/2609.08515/) (2026)
- [Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering](https://mlsanity.com/paper/2609.39701/) (2026)
- [Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric](https://mlsanity.com/paper/2610.17880/) (2026)
- [Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations](https://mlsanity.com/paper/2610.19817/) (2026)

## Abstract (arXiv)

Aligning Large Language Models (LLMs) with human values has attracted increasing attention since it provides clarity, transparency, and the ability to adapt to evolving scenarios. In this paper, we introduce a Controlled Value Vector Activation (ConVA) method that directly aligns the internal values of LLMs by interpreting how a value is encoded in their latent representations and modifies relevant activations to ensure consistent values in LLMs. To ensure an accurate and unbiased interpretation, we propose a context-controlled value vector identification method. To consistently control values without sacrificing model performance, we introduce a gated value vector activation method for effective and minimum degree of value control. Experiments show that our method achieves the highest control success rate across 10 basic values without hurting LLM performance and fluency, and ensures target values even with opposite and potentially malicious input prompts. Source code and data are available at~ https://github.com/hr-jin/ConVA.