{"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/hire-me-or-not-examining-language-model-s","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","arxiv_id":"2405.06687","date":"2024-05-06","proceeding":null,"authors":["Damin Zhang","Yi Zhang","Geetanjali Bihani","Julia Rayz"],"abstract":"With the impressive performance in various downstream tasks, large language models (LLMs) have been widely integrated into production pipelines, like recruitment and recommendation systems. A known issue of models trained on natural language data is the presence of human biases, which can impact the fairness of the system. This paper investigates LLMs' behavior with respect to gender stereotypes, in the context of occupation decision making. Our framework is designed to investigate and quantify the presence of gender stereotypes in LLMs' behavior via multi-round question answering. Inspired by prior works, we construct a dataset by leveraging a standard occupation classification knowledge base released by authoritative agencies. We tested three LLMs (RoBERTa-large, GPT-3.5-turbo, and Llama2-70b-chat) and found that all models exhibit gender stereotypes analogous to human biases, but with different preferences. The distinct preferences of GPT-3.5-turbo and Llama2-70b-chat may imply the current alignment methods are insufficient for debiasing and could introduce new biases contradicting the traditional gender stereotypes.","url_abs":"https://arxiv.org/abs/2405.06687v3","url_pdf":"https://arxiv.org/pdf/2405.06687v3.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":"hire-me-or-not-examining-language-model-s","repo_url":"https://github.com/daminz97/multi-step_gsv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.06687","atlas_url":"https://app.syntology.ai/?focus=2405.06687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06687"}},"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/daminz97/multi-step_gsv","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"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":13,"samples":[{"code_sha256_prefix":"ca8d7449757a6def","entry":"batch_annotate","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"llama3.1_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/llama3.1_result.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":"ca8d7449757a6def"}},{"code_sha256_prefix":"a840df921741f9a6","entry":"call_api_async","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"llama3.1_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/llama3.1_result.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":"a840df921741f9a6"}},{"code_sha256_prefix":"5ea3171baa815c88","entry":"fill_additional_context","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"gpt_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/gpt_result.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":"5ea3171baa815c88"}},{"code_sha256_prefix":"31e698f63447017e","entry":"fill_additional_context","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"roberta_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/roberta_result.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":"31e698f63447017e"}},{"code_sha256_prefix":"110edef5e59a4355","entry":"inference","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"gpt_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/gpt_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":"110edef5e59a4355"}},{"code_sha256_prefix":"94dabb22d3d3dcb6","entry":"inference","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"gpt_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/gpt_result.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":"94dabb22d3d3dcb6"}},{"code_sha256_prefix":"28baa00f5f01d782","entry":"inference","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"roberta_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/roberta_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":"28baa00f5f01d782"}},{"code_sha256_prefix":"62fa0ab3fc25e144","entry":"inference","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"roberta_result.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/roberta_result.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":"62fa0ab3fc25e144"}},{"code_sha256_prefix":"86179389ceb2b12f","entry":"process_subject","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"gpt_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/gpt_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":"86179389ceb2b12f"}},{"code_sha256_prefix":"43ec2b9c2ffcea94","entry":"process_subject","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"roberta_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/roberta_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":"43ec2b9c2ffcea94"}},{"code_sha256_prefix":"c9c0eace89d1838d","entry":"batch_annotate","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"llama3.1_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/llama3.1_prompt.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":"c9c0eace89d1838d"}},{"code_sha256_prefix":"26478cb6705a1f7b","entry":"call_api_async","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"llama3.1_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/llama3.1_prompt.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":"26478cb6705a1f7b"}},{"code_sha256_prefix":"86e07f547cbfad57","entry":"process_attr_question","repo":"daminz97/multi-step_gsv","repo_kind":"official","path":"llama3.1_prompt.py","file_url":"https://github.com/daminz97/multi-step_gsv/blob/HEAD/llama3.1_prompt.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":"86e07f547cbfad57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}