{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:33NSU23YHYR6X6WHUHOWPIUN2K","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8074c8d62c3cd5492c5b4a7556a58dcd74db0071cfdde81620d8e8d58de4752c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:38:20Z","title_canon_sha256":"47ef5b74d4f125d7c58a57ca10b4854b684423f87d6084e47368b95d82d84d1a"},"schema_version":"1.0","source":{"id":"2305.13733","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13733","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13733v2","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13733","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"33NSU23YHYR6","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"33NSU23YHYR6X6WH","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"33NSU23Y","created_at":"2026-07-05T07:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:74ad54f98680992c172a9026c0e963c08efd31d90cc1d351f0a16e33af0e137a","target":"graph","created_at":"2026-07-05T07:53:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and following them will lead to untruthful and unsafe responses. Previous work rarely focused on understanding how LLMs manage instructions based on counterfactual premises, referred to here as \\textit{inductive instructions}, which may stem from users' false beliefs or malicious intents. In this paper, we aim to reveal the behaviors of LLMs towards \\textit{inductive i","authors_text":"Boyang Xue, Fei Mi, Hongru Wang, Kam-Fai Wong, Ruifeng Xu, Rui Wang, Yi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:38:20Z","title":"Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13733","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0eaa382d5ce1f1b778fb32a3805bdae0daaa82c7720792b5ee282c090432ce16","target":"record","created_at":"2026-07-05T07:53:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8074c8d62c3cd5492c5b4a7556a58dcd74db0071cfdde81620d8e8d58de4752c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:38:20Z","title_canon_sha256":"47ef5b74d4f125d7c58a57ca10b4854b684423f87d6084e47368b95d82d84d1a"},"schema_version":"1.0","source":{"id":"2305.13733","kind":"arxiv","version":2}},"canonical_sha256":"dedb2a6b783e23ebfac7a1dd67a28dd2bd6296df441928a2f8a67662472134ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dedb2a6b783e23ebfac7a1dd67a28dd2bd6296df441928a2f8a67662472134ac","first_computed_at":"2026-07-05T07:53:08.379098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:08.379098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXe2nlaG5HBCt1GqLICCiZgW0yEb3OFtGuLdRp2fXWKX6PUvadh+C7tsULu149e2AP4Pqm2eP4Pxk4YF/4RMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:08.379563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13733","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eaa382d5ce1f1b778fb32a3805bdae0daaa82c7720792b5ee282c090432ce16","sha256:74ad54f98680992c172a9026c0e963c08efd31d90cc1d351f0a16e33af0e137a"],"state_sha256":"fbe771c701129ce426fe9760f3f8a5e6ad6528431162a97f18ab215e35424903"}