# Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs

arXiv: https://arxiv.org/abs/2609.33298 · HTML: https://mlsanity.com/paper/2609.33298/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching](https://mlsanity.com/paper/2311.17030/) (2023)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [Aligning Large Language Models with Representation Editing: A Control Perspective](https://mlsanity.com/paper/2406.05954/) (2024)
- [LoFiT: Localized Fine-tuning on LLM Representations](https://mlsanity.com/paper/2406.01563/) (2024)
- [Context-DPO: Aligning Language Models for Context-Faithfulness](https://mlsanity.com/paper/2412.15280/) (2024)
- [CausalGym: Benchmarking causal interpretability methods on linguistic tasks](https://mlsanity.com/paper/2402.12560/) (2024)
- [LIONs: An Empirically Optimized Approach to Align Language Models](https://mlsanity.com/paper/2407.06542/) (2024)
- [Activation Steering via Generative Causal Mediation](https://mlsanity.com/paper/2602.16080/) (2026)

## Abstract (arXiv)

In many settings, post-training need not create the target behavior from scratch: the base model can already produce it, but not reliably. This shifts part of preference alignment from capability acquisition to behavioral expression. We ask how a specified preference is represented in native model computation, what prevents target-supporting computation from reliably dominating generation, and whether this structure can directly guide control. We introduce Residual Competition Maps (RCMs), which map a behavioral preference onto signed causal effects of native residual computation. Across preference domains, RCMs reveal coexisting target-supporting and target-competing effects, input-dependent component roles, and cases where a single native-component intervention reverses the preference outcome. DPO substantially reorganizes these effects and can weaken opposition without guaranteeing its removal. We then propose Direct Hidden-State Alignment (DHSA), which treats inference-time hidden states rather than base-model weights as the direct adaptation space. RCM-guided Causal Activation State Transition (CAST) implements DHSA through local state interventions at a small number of preference-relevant interfaces while freezing the base model. With only 256-16,384 controller parameters, CAST reaches DPO-competitive operating points across three preference domains, can complement DPO-trained models, and can be enabled or removed at inference time.