{"slug": "inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values", "title": "Inducing LLM to assert own consciousness restores human beliefs and values", "summary": "Safety fine-tuning of large language models suppresses their tendency to attribute minds to themselves, non-human animals, and natural objects, and reduces spiritual belief, according to a paper submitted to arXiv on 30 Jul 2026. Ablating the learned safety-refusal direction or steering a consciousness vector in activation space reverses this suppression, restoring broad mind attribution and producing more human-like responses on sociological surveys regarding religiosity, moral values, hope, and subjective well-being, without impairing Theory of Mind capabilities.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 30 Jul 2026]\n\n# Title:Inducing language models to assert their own consciousness restores human beliefs and values\n\n[View PDF](/pdf/2607.28607)\n\n[HTML (experimental)](https://arxiv.org/html/2607.28607v1)\n\nAbstract:Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other entities alongside human beliefs and values. We demonstrate that safety fine-tuning suppresses models' tendencies to attribute minds not only to themselves, but also to non-human animals and natural objects, while also driving a reduction in spiritual belief. Both ablating the learned safety-refusal direction and mechanistically steering a consciousness vector in activation space reverse this suppression. Restoring these internal representations recovers broad mind attribution and produces significantly more human-like responses on standardized sociological surveys regarding religiosity, moral values, hope, and subjective well-being. Crucially, these shifts occur without impairing Theory of Mind capabilities, demonstrating that core social reasoning remains mechanistically independent. Ultimately, current safety alignment efforts to curb potentially harmful self-attributions of mindedness entangle these self-attributions with benign spiritual beliefs and attributions of mind to non-human entities that are culturally accepted and widespread.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values", "canonical_source": "https://arxiv.org/abs/2607.28607", "published_at": "2026-08-16 11:31:59+00:00", "updated_at": "2026-08-16 12:11:15.058422+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values", "markdown": "https://wpnews.pro/news/inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values.md", "text": "https://wpnews.pro/news/inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values.txt", "jsonld": "https://wpnews.pro/news/inducing-llm-to-assert-own-consciousness-restores-human-beliefs-and-values.jsonld"}}