{"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/choire-characterizing-and-predicting-human","title":"Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning","arxiv_id":"2311.08385","date":"2023-11-14","proceeding":null,"authors":["Do Xuan Long","Kenji Kawaguchi","Min-Yen Kan","Nancy F. Chen"],"abstract":"Reasoning and predicting human opinions with large language models (LLMs) is essential yet challenging. Current methods employ role-playing with personae but face two major issues: LLMs are sensitive to even a single irrelevant persona, skewing predictions by up to 30%, and LLMs fail to reason strategically over personae. We propose Chain-of-Opinion (COO), a simple four-step solution modeling which and how to reason with personae, inspired by the Value--Belief--Norm (VBN) theory. COO differentiates between explicit personae (demographics and ideology) and implicit personae (historical opinions), involves: (1) filtering irrelevant attributes from explicit personae, (2) ranking implicit personae into a preferential list for selecting top-k, (3) applying novel VBN reasoning to extract user environmental and personal value, belief, and norm variables for accurate and reliable predictions, and (4) iterating VBN reasoning with progressively larger lists of implicit personae to handle potential persona insufficiency. COO efficiently achieves new state-of-the-art opinion prediction via prompting with only 5 inference calls, improving prior techniques by up to 4%. Notably, fine-tuning LMs with COO data results in significantly better opinion-aligned models, by up to 23%.","url_abs":"https://arxiv.org/abs/2311.08385v5","url_pdf":"https://arxiv.org/pdf/2311.08385v5.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":"choire-characterizing-and-predicting-human","repo_url":"https://github.com/dxlong2000/coo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.08385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08385"}},"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/dxlong2000/coo","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"8e09cbcc3b1d8756","entry":"early_stopping","repo":"dxlong2000/coo","repo_kind":"official","path":"src/coo_main.py","file_url":"https://github.com/dxlong2000/coo/blob/HEAD/src/coo_main.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":"8e09cbcc3b1d8756"}},{"code_sha256_prefix":"8488b9390e03f52a","entry":"is_chat_based_agent","repo":"dxlong2000/coo","repo_kind":"official","path":"src/gptinference/openai_api.py","file_url":"https://github.com/dxlong2000/coo/blob/HEAD/src/gptinference/openai_api.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":"8488b9390e03f52a"}},{"code_sha256_prefix":"91a346890319e7f8","entry":"take","repo":"dxlong2000/coo","repo_kind":"official","path":"src/gptinference/utils.py","file_url":"https://github.com/dxlong2000/coo/blob/HEAD/src/gptinference/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91a346890319e7f8"}},{"code_sha256_prefix":"bca7e60898ab2cab","entry":"write_json","repo":"dxlong2000/coo","repo_kind":"official","path":"src/gptinference/utils.py","file_url":"https://github.com/dxlong2000/coo/blob/HEAD/src/gptinference/utils.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":"bca7e60898ab2cab"}},{"code_sha256_prefix":"b4ff714c7a077bf4","entry":"write_jsonl","repo":"dxlong2000/coo","repo_kind":"official","path":"src/gptinference/utils.py","file_url":"https://github.com/dxlong2000/coo/blob/HEAD/src/gptinference/utils.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":"b4ff714c7a077bf4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}