通过价值移植引导语言模型目标

Computer Science > Machine Learning arXiv:2609.34056 (cs) [Submitted on 28 Sep 2026] Title:Steering Language Model Goals with Value Transplant Authors:Pengcheng Jiang, Fabien Roger View a PDF of the paper titled Steering Language Model Goals with Value Transplant, by Pengcheng Jiang and 1 other authors View PDF HTML (experimental) Abstract: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. Comments: Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL) Cite as: arXiv:2609.34056 [cs.LG] (or arXiv:2609.34056v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2609.34056 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Pengcheng Jiang [view email] [v1] Mon, 28 Sep 2026 00:26:19 UTC (5,693 KB) Full-text links: Access Paper: View a PDF of the paper titled Steering Language Model Goals with Value Transplant, by Pengcheng Jiang and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-09 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)