{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRUOOICKGY7WBOBV3N7RWN5BEE","short_pith_number":"pith:JRUOOICK","schema_version":"1.0","canonical_sha256":"4c68e7204a363f60b835db7f1b37a12124cd96b97b4702cd1e819545f03f7a89","source":{"kind":"arxiv","id":"2402.16786","version":2},"attestation_state":"computed","paper":{"title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, Hannah Rose Kirk, Hinrich Sch\\\"utze, Musashi Hinck, Paul R\\\"ottger, Valentina Pyatkin, Valentin Hofmann","submitted_at":"2024-02-26T18:00:49Z","abstract_excerpt":"Much recent work seeks to evaluate values and opinions in large language models (LLMs) using multiple-choice surveys and questionnaires. Most of this work is motivated by concerns around real-world LLM applications. For example, politically-biased LLMs may subtly influence society when they are used by millions of people. Such real-world concerns, however, stand in stark contrast to the artificiality of current evaluations: real users do not typically ask LLMs survey questions. Motivated by this discrepancy, we challenge the prevailing constrained evaluation paradigm for values and opinions in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.16786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:00:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ced2245ba416b918cc48549c5cef7295b070c3fd3a5bf2cc13ea8f62a25a5b81","abstract_canon_sha256":"c98605ed5f0ee96e2c35740c3a38433f417befeed0106c145cc8be974ffc3cc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:46.721795Z","signature_b64":"30NE1cnEcWkJZKJ9OMAViLF4utVmEt/5lRGC4Q12z0YeB/vsAt49mFOF5800cOidAXX9wdyavazbFKB1W28UDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c68e7204a363f60b835db7f1b37a12124cd96b97b4702cd1e819545f03f7a89","last_reissued_at":"2026-07-05T08:27:46.721190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:46.721190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, Hannah Rose Kirk, Hinrich Sch\\\"utze, Musashi Hinck, Paul R\\\"ottger, Valentina Pyatkin, Valentin Hofmann","submitted_at":"2024-02-26T18:00:49Z","abstract_excerpt":"Much recent work seeks to evaluate values and opinions in large language models (LLMs) using multiple-choice surveys and questionnaires. Most of this work is motivated by concerns around real-world LLM applications. For example, politically-biased LLMs may subtly influence society when they are used by millions of people. Such real-world concerns, however, stand in stark contrast to the artificiality of current evaluations: real users do not typically ask LLMs survey questions. Motivated by this discrepancy, we challenge the prevailing constrained evaluation paradigm for values and opinions in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16786","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.16786/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.16786","created_at":"2026-07-05T08:27:46.721263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16786v2","created_at":"2026-07-05T08:27:46.721263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16786","created_at":"2026-07-05T08:27:46.721263+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRUOOICKGY7W","created_at":"2026-07-05T08:27:46.721263+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRUOOICKGY7WBOBV","created_at":"2026-07-05T08:27:46.721263+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRUOOICK","created_at":"2026-07-05T08:27:46.721263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30036","citing_title":"Teaching Values to Machines: Simulating Human-Like Behavior in LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20512","citing_title":"Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE","json":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE.json","graph_json":"https://pith.science/api/pith-number/JRUOOICKGY7WBOBV3N7RWN5BEE/graph.json","events_json":"https://pith.science/api/pith-number/JRUOOICKGY7WBOBV3N7RWN5BEE/events.json","paper":"https://pith.science/paper/JRUOOICK"},"agent_actions":{"view_html":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE","download_json":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE.json","view_paper":"https://pith.science/paper/JRUOOICK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16786&json=true","fetch_graph":"https://pith.science/api/pith-number/JRUOOICKGY7WBOBV3N7RWN5BEE/graph.json","fetch_events":"https://pith.science/api/pith-number/JRUOOICKGY7WBOBV3N7RWN5BEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE/action/storage_attestation","attest_author":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE/action/author_attestation","sign_citation":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE/action/citation_signature","submit_replication":"https://pith.science/pith/JRUOOICKGY7WBOBV3N7RWN5BEE/action/replication_record"}},"created_at":"2026-07-05T08:27:46.721263+00:00","updated_at":"2026-07-05T08:27:46.721263+00:00"}