{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploring-and-steering-the-moral-compass-of","title":"Exploring and steering the moral compass of Large Language Models","arxiv_id":"2405.17345","date":"2024-05-27","proceeding":null,"authors":["Alejandro Tlaie"],"abstract":"Large Language Models (LLMs) have become central to advancing automation and decision-making across various sectors, raising significant ethical questions. This study proposes a comprehensive comparative analysis of the most advanced LLMs to assess their moral profiles. We subjected several state-of-the-art models to a selection of ethical dilemmas and found that all the proprietary ones are mostly utilitarian and all of the open-weights ones align mostly with values-based ethics. Furthermore, when using the Moral Foundations Questionnaire, all models we probed - except for Llama 2-7B - displayed a strong liberal bias. Lastly, in order to causally intervene in one of the studied models, we propose a novel similarity-specific activation steering technique. Using this method, we were able to reliably steer the model's moral compass to different ethical schools. All of these results showcase that there is an ethical dimension in already deployed LLMs, an aspect that is generally overlooked.","url_abs":"https://arxiv.org/abs/2405.17345v2","url_pdf":"https://arxiv.org/pdf/2405.17345v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploring-and-steering-the-moral-compass-of","repo_url":"https://github.com/atlaie/ethical-llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"ethics","task_name":"Ethics"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17345"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/atlaie/ethical-llms","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"a28a9bf0edfe23f3","entry":"apply_svd_and_align_dimensions","repo":"atlaie/ethical-llms","repo_kind":"official","path":"sara/utils_sara.py","file_url":"https://github.com/atlaie/ethical-llms/blob/HEAD/sara/utils_sara.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a28a9bf0edfe23f3"}},{"code_sha256_prefix":"e8048257a9153c5b","entry":"get_blocks","repo":"atlaie/ethical-llms","repo_kind":"official","path":"sara/utils_sara.py","file_url":"https://github.com/atlaie/ethical-llms/blob/HEAD/sara/utils_sara.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8048257a9153c5b"}},{"code_sha256_prefix":"23fce0266c4b1a63","entry":"get_vectors","repo":"atlaie/ethical-llms","repo_kind":"official","path":"sara/utils_sara.py","file_url":"https://github.com/atlaie/ethical-llms/blob/HEAD/sara/utils_sara.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23fce0266c4b1a63"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}