{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TGZ5S7HDCY3D3UQZQZPX4F3V6A","short_pith_number":"pith:TGZ5S7HD","schema_version":"1.0","canonical_sha256":"99b3d97ce316363dd219865f7e1775f03b29db387896f89f330b25865e253455","source":{"kind":"arxiv","id":"2407.12043","version":2},"attestation_state":"computed","paper":{"title":"The Art of Saying No: Contextual Noncompliance in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, Faeze Brahman, Hannaneh Hajishirzi, Jack Hessel, Khyathi Chandu, Noah A. Smith, Nouha Dziri, Pradeep Dasigi, Sachin Kumar, Sarah Wiegreffe, Valentina Pyatkin, Vidhisha Balachandran, Yejin Choi, Yulia Tsvetkov","submitted_at":"2024-07-02T07:12:51Z","abstract_excerpt":"Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of \"unsafe\" queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this "},"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":"2407.12043","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:12:51Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"9b6d510ddacb2983d9327ab41abb23ffccdac172446924f17d81926a66b982ce","abstract_canon_sha256":"398e2ff89c13a10e7e495a9809407f6a1f71f6333fce3fc640717cf7effa2268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:08.050621Z","signature_b64":"lX3oKs5pfr3EC0FgPavvxhnoL7OPFOQxl9/EdJPMHGRtI0jJdAalfph8/bZSgtPvgb4We50S2XcsU4L6wjlFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99b3d97ce316363dd219865f7e1775f03b29db387896f89f330b25865e253455","last_reissued_at":"2026-07-05T09:39:08.050106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:08.050106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Art of Saying No: Contextual Noncompliance in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, Faeze Brahman, Hannaneh Hajishirzi, Jack Hessel, Khyathi Chandu, Noah A. Smith, Nouha Dziri, Pradeep Dasigi, Sachin Kumar, Sarah Wiegreffe, Valentina Pyatkin, Vidhisha Balachandran, Yejin Choi, Yulia Tsvetkov","submitted_at":"2024-07-02T07:12:51Z","abstract_excerpt":"Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of \"unsafe\" queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12043","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/2407.12043/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":"2407.12043","created_at":"2026-07-05T09:39:08.050170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12043v2","created_at":"2026-07-05T09:39:08.050170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12043","created_at":"2026-07-05T09:39:08.050170+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGZ5S7HDCY3D","created_at":"2026-07-05T09:39:08.050170+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGZ5S7HDCY3D3UQZ","created_at":"2026-07-05T09:39:08.050170+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGZ5S7HD","created_at":"2026-07-05T09:39:08.050170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07916","citing_title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15000","citing_title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00869","citing_title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02574","citing_title":"LLM-Safety Evaluations Lack Robustness","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21545","citing_title":"RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22764","citing_title":"Implicit Humanization in Everyday LLM Moral Judgments","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06233","citing_title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18473","citing_title":"Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A","json":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A.json","graph_json":"https://pith.science/api/pith-number/TGZ5S7HDCY3D3UQZQZPX4F3V6A/graph.json","events_json":"https://pith.science/api/pith-number/TGZ5S7HDCY3D3UQZQZPX4F3V6A/events.json","paper":"https://pith.science/paper/TGZ5S7HD"},"agent_actions":{"view_html":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A","download_json":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A.json","view_paper":"https://pith.science/paper/TGZ5S7HD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12043&json=true","fetch_graph":"https://pith.science/api/pith-number/TGZ5S7HDCY3D3UQZQZPX4F3V6A/graph.json","fetch_events":"https://pith.science/api/pith-number/TGZ5S7HDCY3D3UQZQZPX4F3V6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A/action/storage_attestation","attest_author":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A/action/author_attestation","sign_citation":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A/action/citation_signature","submit_replication":"https://pith.science/pith/TGZ5S7HDCY3D3UQZQZPX4F3V6A/action/replication_record"}},"created_at":"2026-07-05T09:39:08.050170+00:00","updated_at":"2026-07-05T09:39:08.050170+00:00"}