{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OGKI3YRRS5ELPHKH3TH3PYAI5Z","short_pith_number":"pith:OGKI3YRR","schema_version":"1.0","canonical_sha256":"71948de2319748b79d47dccfb7e008ee51963995123fc3f609ec883787d17295","source":{"kind":"arxiv","id":"2411.12405","version":2},"attestation_state":"computed","paper":{"title":"Evaluating the Prompt Steerability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Djallel Bouneffouf, Elizabeth M. Daly, Erik Miehling, Jesus Rios, Karthikeyan Natesan Ramamurthy, Miao Liu, Michael Desmond, Pierre Dognin","submitted_at":"2024-11-19T10:41:54Z","abstract_excerpt":"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 inspectin"},"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":"2411.12405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T10:41:54Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"c46707231a9c9bfaf208af8a3c71c629e64e31c20d5f6bc0e1ee838e00d37cbb","abstract_canon_sha256":"e3f93cfb4e64bdd9f2025a6a926c2b36d101dd0020a4bf2812ce6516a9bce514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:48.112735Z","signature_b64":"SXfDsF6DiQYRDYm+a+czpM4t8xqMGX1uwpCRtQCv9PcYgiy0qPEzAAYRRxSHhfZEHRtPtjKIDR/C18Vv9QqRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71948de2319748b79d47dccfb7e008ee51963995123fc3f609ec883787d17295","last_reissued_at":"2026-07-05T10:14:48.112249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:48.112249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Prompt Steerability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Djallel Bouneffouf, Elizabeth M. Daly, Erik Miehling, Jesus Rios, Karthikeyan Natesan Ramamurthy, Miao Liu, Michael Desmond, Pierre Dognin","submitted_at":"2024-11-19T10:41:54Z","abstract_excerpt":"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 inspectin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12405","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/2411.12405/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":"2411.12405","created_at":"2026-07-05T10:14:48.112300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12405v2","created_at":"2026-07-05T10:14:48.112300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12405","created_at":"2026-07-05T10:14:48.112300+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGKI3YRRS5EL","created_at":"2026-07-05T10:14:48.112300+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGKI3YRRS5ELPHKH","created_at":"2026-07-05T10:14:48.112300+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGKI3YRR","created_at":"2026-07-05T10:14:48.112300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20572","citing_title":"Investigating Linguistic Steering: An Analysis of Adjectival Effects Across Large Language Model Architectures","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24079","citing_title":"The Pragmatic Persona: Discovering LLM Persona through Bridging Inference","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z","json":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z.json","graph_json":"https://pith.science/api/pith-number/OGKI3YRRS5ELPHKH3TH3PYAI5Z/graph.json","events_json":"https://pith.science/api/pith-number/OGKI3YRRS5ELPHKH3TH3PYAI5Z/events.json","paper":"https://pith.science/paper/OGKI3YRR"},"agent_actions":{"view_html":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z","download_json":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z.json","view_paper":"https://pith.science/paper/OGKI3YRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12405&json=true","fetch_graph":"https://pith.science/api/pith-number/OGKI3YRRS5ELPHKH3TH3PYAI5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/OGKI3YRRS5ELPHKH3TH3PYAI5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z/action/storage_attestation","attest_author":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z/action/author_attestation","sign_citation":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z/action/citation_signature","submit_replication":"https://pith.science/pith/OGKI3YRRS5ELPHKH3TH3PYAI5Z/action/replication_record"}},"created_at":"2026-07-05T10:14:48.112300+00:00","updated_at":"2026-07-05T10:14:48.112300+00:00"}