# Steering Language Model Goals with Value Transplant

arXiv: https://arxiv.org/abs/2609.34056 · HTML: https://mlsanity.com/paper/2609.34056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 14 of 14)

- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI](https://mlsanity.com/paper/2511.01689/) (2025)
- [Understanding and Controlling a Maze-Solving Policy Network](https://mlsanity.com/paper/2310.08043/) (2023)
- [The Value Axis: Language Models Encode Whether They're on the Right Track](https://mlsanity.com/paper/2606.17056/) (2026)
- [How's it going? Reinforcement learning in language models recruits a functional welfare axis](https://mlsanity.com/paper/2605.30232/) (2026)

## Abstract (arXiv)

Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previous work has examined how models may internally track their progress toward their goals through a "value axis." We study whether changing such a signal can retarget the model's search toward a different goal. We test value transplant: at each token, we shift the host model's activation along a candidate value axis by the donor-host difference in value coordinates (multiplied by a large scalar), aiming to redirect the host toward the donor's goal. We study this intervention in Qwen3-8B and GPT-OSS-20B models fine-tuned into honest and cheating variants. We test several candidate value axes, including a self-rating axis constructed from activations preceding high versus low elicited self-ratings of progress. The intervention works in both directions, with an honest donor reducing test-gaming in a cheating host and a cheating donor increasing test-gaming in an honest host, showing that this signal can influence which strategy the model follows. On solvable coding tasks, transplant from an honest donor also improves the cheating host's hidden-test performance. Value transplant also works across model families, providing preliminary evidence for the intervention in a setting relevant to model control.