# VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment

arXiv: https://arxiv.org/abs/2603.04822 · HTML: https://mlsanity.com/paper/2603.04822/

## Key facts

- No citing papers in the map yet (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 24 of its 56 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## 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, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Mitigating the Alignment Tax of RLHF](https://mlsanity.com/paper/2309.06256/) (2023)
- [ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts](https://mlsanity.com/paper/2110.01799/) (2021)
- [Learning from Dialogue after Deployment: Feed Yourself, Chatbot!](https://mlsanity.com/paper/1901.05415/) (2019)
- [A Survey of Personalized Large Language Models: Progress and Future Directions](https://mlsanity.com/paper/2502.11528/) (2025)
- [PAD: Personalized Alignment of LLMs at Decoding-Time](https://mlsanity.com/paper/2410.04070/) (2024)
- [A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs](https://mlsanity.com/paper/2506.13245/) (2025)
- [A Review of Bilevel Optimization: Methods, Emerging Applications, and Recent Advancements](https://mlsanity.com/paper/2511.03448/) (2025)
- [Meta-Learning via Feature-Label Memory Network](https://mlsanity.com/paper/1710.07110/) (2017)

## Abstract (arXiv)

Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handle only coarse-grained attributes. In practice, fine-tuning LLMs on task-specific datasets to optimize value alignment inevitably incurs an alignment tax: the model's pre-calibrated value system drifts significantly due to latent bias absorption from training data, while the fine-tuning process also causes severe hallucinations and semantic information loss in generated responses. To address this, we propose VISA (Value Injection via Shielded Adaptation), a closed-loop framework designed to navigate this trade-off. VISA's architecture features a high-precision value detector, a semantic-to-value translator, and a core value-rewriter. The value-rewriter is trained via Group Relative Policy Optimization (GRPO) with a composite reward function that simultaneously optimizes for fine-grained value precision, and the preservation of semantic integrity. By learning an optimal policy to balance these competing objectives, VISA effectively mitigates the alignment tax while staying loyal to the original knowledge. Our experiments demonstrate that this approach enables precise control over a model's value expression while maintaining its factual consistency and general capabilities, significantly outperforming both standard fine-tuning methods and prompting-based baselines, including GPT-4o.