{"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/llm-measure-generating-valid-consistent-and","title":"LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research","arxiv_id":"2409.12722","date":"2024-09-19","proceeding":null,"authors":["Yi Yang","Hanyu Duan","Jiaxin Liu","Kar Yan Tam"],"abstract":"The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.","url_abs":"https://arxiv.org/abs/2409.12722v1","url_pdf":"https://arxiv.org/pdf/2409.12722v1.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":"llm-measure-generating-valid-consistent-and","repo_url":"https://github.com/hduanac/llm-measure","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.12722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12722"}},"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/hduanac/llm-measure","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"93e9dfb73cce5a2f","entry":"do_inference","repo":"hduanac/llm-measure","repo_kind":"official","path":"corporateInnovation/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/corporateInnovation/llm_measure.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":"93e9dfb73cce5a2f"}},{"code_sha256_prefix":"92f94141233d782c","entry":"do_inference","repo":"hduanac/llm-measure","repo_kind":"official","path":"fedMonetaryPolicyStance/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/fedMonetaryPolicyStance/llm_measure.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":"92f94141233d782c"}},{"code_sha256_prefix":"8c9693236503cbec","entry":"do_inference","repo":"hduanac/llm-measure","repo_kind":"official","path":"informationOverload/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/informationOverload/llm_measure.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":"8c9693236503cbec"}},{"code_sha256_prefix":"f6555bbbc313d9fe","entry":"identify_concept_vector","repo":"hduanac/llm-measure","repo_kind":"official","path":"corporateInnovation/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/corporateInnovation/llm_measure.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":"f6555bbbc313d9fe"}},{"code_sha256_prefix":"673bc90d21947923","entry":"identify_concept_vector","repo":"hduanac/llm-measure","repo_kind":"official","path":"fedMonetaryPolicyStance/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/fedMonetaryPolicyStance/llm_measure.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":"673bc90d21947923"}},{"code_sha256_prefix":"cb0976a02281bbe5","entry":"identify_concept_vector","repo":"hduanac/llm-measure","repo_kind":"official","path":"informationOverload/llm_measure.py","file_url":"https://github.com/hduanac/llm-measure/blob/HEAD/informationOverload/llm_measure.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":"cb0976a02281bbe5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}