# Pref-CTRL: Preference Driven LLM Alignment using Representation Editing

arXiv: https://arxiv.org/abs/2604.23543 · HTML: https://mlsanity.com/paper/2604.23543/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [ARGS: Alignment as Reward-Guided Search](https://mlsanity.com/paper/2402.01694/) (2024)
- [Aligner: Efficient Alignment by Learning to Correct](https://mlsanity.com/paper/2402.02416/) (2024)
- [On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization](https://mlsanity.com/paper/2405.16455/) (2024)
- [Aligning Large Language Models with Representation Editing: A Control Perspective](https://mlsanity.com/paper/2406.05954/) (2024)
- [Spectral Editing of Activations for Large Language Model Alignment](https://mlsanity.com/paper/2405.09719/) (2024)
- [GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment](https://mlsanity.com/paper/2410.08193/) (2024)
- [Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment](https://mlsanity.com/paper/2408.06266/) (2024)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [Towards Scalable Automated Alignment of LLMs: A Survey](https://mlsanity.com/paper/2406.01252/) (2024)
- [Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs](https://mlsanity.com/paper/2502.19148/) (2025)
- [PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model](https://mlsanity.com/paper/2505.06274/) (2025)
- [Online Preference Alignment for Language Models via Count-based Exploration](https://mlsanity.com/paper/2501.12735/) (2025)
- [Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model](https://mlsanity.com/paper/2403.19443/) (2024)
- [Learning to Reason from Feedback at Test-Time](https://mlsanity.com/paper/2502.15771/) (2025)

## Abstract (arXiv)

Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a prominent and effective approach, RE-Control (Kong et al., 2024), has proposed leveraging an external value function trained over the LLM's hidden states to guide generation via gradient-based editing. While effective, this method overlooks a key characteristic of alignment tasks, i.e. that they are typically formulated as learning from human preferences between candidate responses. To address this, in this paper we propose a novel preference-based training framework, Pref-CTRL, that uses a multi-objective value function to better reflect the structure of preference data. Our approach has outperformed RE-Control on two benchmark datasets and showed greater generalization on out-of-domain datasets. Our source code is available at https://github.com/UTS-nlPUG/pref-ctrl.