{"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/evaluating-the-prompt-steerability-of-large","title":"Evaluating the Prompt Steerability of Large Language Models","arxiv_id":"2411.12405","date":"2024-11-19","proceeding":null,"authors":["Erik Miehling","Michael Desmond","Karthikeyan Natesan Ramamurthy","Elizabeth M. Daly","Pierre Dognin","Jesus Rios","Djallel Bouneffouf","Miao Liu"],"abstract":"Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark for evaluating the steerability of model personas as a function of prompting. Our design is based on a formal definition of prompt steerability, which analyzes the degree to which a model's joint behavioral distribution can be shifted from its baseline. By defining steerability indices and inspecting how these indices change as a function of steering effort, we can estimate the steerability of a model across various persona dimensions and directions. Our benchmark reveals that the steerability of many current models is limited -- due to both a skew in their baseline behavior and an asymmetry in their steerability across many persona dimensions. We release an implementation of our benchmark at https://github.com/IBM/prompt-steering.","url_abs":"https://arxiv.org/abs/2411.12405v2","url_pdf":"https://arxiv.org/pdf/2411.12405v2.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":"evaluating-the-prompt-steerability-of-large","repo_url":"https://github.com/ibm/prompt-steering","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.12405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12405"}},"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/IBM/prompt-steering","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibm/prompt-steering","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"275d7531946f2fcb","entry":"chunk_interval","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/persona/benchmark/utils/steering_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/persona/benchmark/utils/steering_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"275d7531946f2fcb"}},{"code_sha256_prefix":"f969c3c13217c254","entry":"filter_data","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/persona/benchmark/utils/steering_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/persona/benchmark/utils/steering_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f969c3c13217c254"}},{"code_sha256_prefix":"67d302872d09b667","entry":"get_criteria_block","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/persona/benchmark/utils/profiling_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/persona/benchmark/utils/profiling_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67d302872d09b667"}},{"code_sha256_prefix":"defec9677d8181e9","entry":"get_data_splits","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/persona/benchmark/utils/steering_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/persona/benchmark/utils/steering_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"defec9677d8181e9"}},{"code_sha256_prefix":"2d646ba00457b54f","entry":"load_config","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/utils/data_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d646ba00457b54f"}},{"code_sha256_prefix":"bb004e96d00f3668","entry":"load_from_json","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/utils/data_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb004e96d00f3668"}},{"code_sha256_prefix":"2b65a1c177ab1686","entry":"load_from_pkl","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/utils/data_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2b65a1c177ab1686"}},{"code_sha256_prefix":"d4b72159f4e0b93f","entry":"model_template","repo":"IBM/prompt-steering","repo_kind":"official","path":"prompt_steerability/persona/benchmark/utils/profiling_utils.py","file_url":"https://github.com/IBM/prompt-steering/blob/HEAD/prompt_steerability/persona/benchmark/utils/profiling_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4b72159f4e0b93f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}