{"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/neuron-based-personality-trait-induction-in","title":"Neuron-based Personality Trait Induction in Large Language Models","arxiv_id":"2410.12327","date":"2024-10-16","proceeding":null,"authors":["Jia Deng","Tianyi Tang","Yanbin Yin","Wenhao Yang","Wayne Xin Zhao","Ji-Rong Wen"],"abstract":"Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we present a neuron-based approach for personality trait induction in LLMs, with three major technical contributions. First, we construct PersonalityBench, a large-scale dataset for identifying and evaluating personality traits in LLMs. This dataset is grounded in the Big Five personality traits from psychology and is designed to assess the generative capabilities of LLMs towards specific personality traits. Second, by leveraging PersonalityBench, we propose an efficient method for identifying personality-related neurons within LLMs by examining the opposite aspects of a given trait. Third, we develop a simple yet effective induction method that manipulates the values of these identified personality-related neurons. This method enables fine-grained control over the traits exhibited by LLMs without training and modifying model parameters. Extensive experiments validate the efficacy of our neuron identification and trait induction methods. Notably, our approach achieves comparable performance as fine-tuned models, offering a more efficient and flexible solution for personality trait induction in LLMs. We provide access to all the mentioned resources at https://github.com/RUCAIBox/NPTI.","url_abs":"https://arxiv.org/abs/2410.12327v1","url_pdf":"https://arxiv.org/pdf/2410.12327v1.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":"neuron-based-personality-trait-induction-in","repo_url":"https://github.com/RUCAIBox/NPTI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12327"}},"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":"deterministic:regex_extraction","url":"https://github.com/RUCAIBox/NPTI","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"a93bd5cf26471fb2","entry":"get_data","repo":"rucaibox/npti","repo_kind":"official","path":"NPTI/code/gpt4_score.py","file_url":"https://github.com/rucaibox/npti/blob/HEAD/NPTI/code/gpt4_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a93bd5cf26471fb2"}},{"code_sha256_prefix":"e99e696d946a6e00","entry":"calculate_quantiles","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/process_neuron.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/process_neuron.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":"e99e696d946a6e00"}},{"code_sha256_prefix":"0ec62f26ce89387a","entry":"factory","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/baseline_prompt.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/baseline_prompt.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":"0ec62f26ce89387a"}},{"code_sha256_prefix":"6340f1429608e7df","entry":"get_prompt","repo":"rucaibox/npti","repo_kind":"official","path":"NPTI/code/gpt4_score.py","file_url":"https://github.com/rucaibox/npti/blob/HEAD/NPTI/code/gpt4_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6340f1429608e7df"}},{"code_sha256_prefix":"1b6f700d976acdaa","entry":"load_neuron_to_change","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/answer_question_change_neuron.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/answer_question_change_neuron.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":"1b6f700d976acdaa"}},{"code_sha256_prefix":"51373bec75991d57","entry":"load_question","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/answer_question_change_neuron.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/answer_question_change_neuron.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":"51373bec75991d57"}},{"code_sha256_prefix":"29f8d58533fdb57e","entry":"read_and_convert_to_dict","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/process_neuron.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/process_neuron.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":"29f8d58533fdb57e"}},{"code_sha256_prefix":"a277bdb894d81f0a","entry":"get_completion","repo":"RUCAIBox/NPTI","repo_kind":"official","path":"NPTI/code/gpt4_score.py","file_url":"https://github.com/RUCAIBox/NPTI/blob/HEAD/NPTI/code/gpt4_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a277bdb894d81f0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}