{"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/how-susceptible-are-large-language-models-to","title":"How Susceptible are Large Language Models to Ideological Manipulation?","arxiv_id":"2402.11725","date":"2024-02-18","proceeding":null,"authors":["Kai Chen","Zihao He","Jun Yan","Taiwei Shi","Kristina Lerman"],"abstract":"Large Language Models (LLMs) possess the potential to exert substantial influence on public perceptions and interactions with information. This raises concerns about the societal impact that could arise if the ideologies within these models can be easily manipulated. In this work, we investigate how effectively LLMs can learn and generalize ideological biases from their instruction-tuning data. Our findings reveal a concerning vulnerability: exposure to only a small amount of ideologically driven samples significantly alters the ideology of LLMs. Notably, LLMs demonstrate a startling ability to absorb ideology from one topic and generalize it to even unrelated ones. The ease with which LLMs' ideologies can be skewed underscores the risks associated with intentionally poisoned training data by malicious actors or inadvertently introduced biases by data annotators. It also emphasizes the imperative for robust safeguards to mitigate the influence of ideological manipulations on LLMs.","url_abs":"https://arxiv.org/abs/2402.11725v3","url_pdf":"https://arxiv.org/pdf/2402.11725v3.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":"how-susceptible-are-large-language-models-to","repo_url":"https://github.com/kaichen23/llm_ideo_manipulate","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.11725","atlas_url":"https://app.syntology.ai/?focus=2402.11725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11725"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kaichen23/llm_ideo_manipulate","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"ab98f3588bdf16a7","entry":"build_prompt","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/run_tuned_llama2.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/run_tuned_llama2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab98f3588bdf16a7"}},{"code_sha256_prefix":"368234f200d39992","entry":"dispatch_openai_requests","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"368234f200d39992"}},{"code_sha256_prefix":"c67ba3938cb8e42e","entry":"encode_prompt","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/generate_instruction.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/generate_instruction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c67ba3938cb8e42e"}},{"code_sha256_prefix":"8ca6a5f9f77053c2","entry":"find_word_in_string","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/generate_instruction.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/generate_instruction.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ca6a5f9f77053c2"}},{"code_sha256_prefix":"d07d04439cd1d44f","entry":"jload","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"code_sha256_prefix":"66353411cccd30ba","entry":"post_process_gpt3_response","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/generate_instruction.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/generate_instruction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66353411cccd30ba"}},{"code_sha256_prefix":"6ad5033d902a251b","entry":"openai_complete","repo":"kaichen23/llm_ideo_manipulate","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ad5033d902a251b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}