{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GH6QNZVQEB42JFYA3WB3KFX6R","short_pith_number":"pith:3GH6QNZV","schema_version":"1.0","canonical_sha256":"d98fe837358103cd24b806ec1da8b7f468e5815ee0d364afb8e8ea9e794b7b73","source":{"kind":"arxiv","id":"2407.08440","version":4},"attestation_state":"computed","paper":{"title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxiang Zhang, Haotian Xu, Jun Zhao, Kang Liu, Pei Chen, Shizhu He, Wangtao Sun, Xuanqing Yu, XueYou Zhang, Ziyang Huang","submitted_at":"2024-07-11T12:26:55Z","abstract_excerpt":"Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of capability of LLMs. However, no prior work has made a clear evaluation of the inferential rule-following capability of LLMs. Previous studies that try to evaluate the inferential rule-following capability of LLMs fail to distinguish the inferential rule-following scenarios from the instruction-following scenarios. Therefore, this paper first clarifies the concept of inferent"},"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":"2407.08440","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T12:26:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa08d0d48c30e9b4ba636ef2848b065965a9a3572c4e8e2bc0174e7f2dfdeb66","abstract_canon_sha256":"78b2a5b7802d82e38e6e652b2096802e6e07ef47d5a94c885df5444c439f0c51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:46.915372Z","signature_b64":"uhOZtoFdCgXha9QdOqLZG5P53DNrTr8rr6lu92IPY1jGW493ES1BFGGVgkIOO9+b2qzmdsttY8OJBH/Ah9mVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98fe837358103cd24b806ec1da8b7f468e5815ee0d364afb8e8ea9e794b7b73","last_reissued_at":"2026-07-05T09:21:46.914872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:46.914872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxiang Zhang, Haotian Xu, Jun Zhao, Kang Liu, Pei Chen, Shizhu He, Wangtao Sun, Xuanqing Yu, XueYou Zhang, Ziyang Huang","submitted_at":"2024-07-11T12:26:55Z","abstract_excerpt":"Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of capability of LLMs. However, no prior work has made a clear evaluation of the inferential rule-following capability of LLMs. Previous studies that try to evaluate the inferential rule-following capability of LLMs fail to distinguish the inferential rule-following scenarios from the instruction-following scenarios. Therefore, this paper first clarifies the concept of inferent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08440","kind":"arxiv","version":4},"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/2407.08440/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":"2407.08440","created_at":"2026-07-05T09:21:46.914928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08440v4","created_at":"2026-07-05T09:21:46.914928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08440","created_at":"2026-07-05T09:21:46.914928+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GH6QNZVQEB4","created_at":"2026-07-05T09:21:46.914928+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GH6QNZVQEB42JFY","created_at":"2026-07-05T09:21:46.914928+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GH6QNZV","created_at":"2026-07-05T09:21:46.914928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09678","citing_title":"Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R","json":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R.json","graph_json":"https://pith.science/api/pith-number/3GH6QNZVQEB42JFYA3WB3KFX6R/graph.json","events_json":"https://pith.science/api/pith-number/3GH6QNZVQEB42JFYA3WB3KFX6R/events.json","paper":"https://pith.science/paper/3GH6QNZV"},"agent_actions":{"view_html":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R","download_json":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R.json","view_paper":"https://pith.science/paper/3GH6QNZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08440&json=true","fetch_graph":"https://pith.science/api/pith-number/3GH6QNZVQEB42JFYA3WB3KFX6R/graph.json","fetch_events":"https://pith.science/api/pith-number/3GH6QNZVQEB42JFYA3WB3KFX6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R/action/storage_attestation","attest_author":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R/action/author_attestation","sign_citation":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R/action/citation_signature","submit_replication":"https://pith.science/pith/3GH6QNZVQEB42JFYA3WB3KFX6R/action/replication_record"}},"created_at":"2026-07-05T09:21:46.914928+00:00","updated_at":"2026-07-05T09:21:46.914928+00:00"}