{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:47QXUP5KFGIIGHMAMDMSO4D64I","short_pith_number":"pith:47QXUP5K","schema_version":"1.0","canonical_sha256":"e7e17a3faa2990831d8060d927707ee22ba1f8047ec4821bbcc57e81e5ed9f15","source":{"kind":"arxiv","id":"2311.08147","version":1},"attestation_state":"computed","paper":{"title":"RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Hao Zhou, Jie Zhou, Lianzhe Huang, Shicheng Li, Sishuo Chen, Xu Sun, Yi Liu","submitted_at":"2023-11-14T13:24:19Z","abstract_excerpt":"LLMs and AI chatbots have improved people's efficiency in various fields. However, the necessary knowledge for answering the question may be beyond the models' knowledge boundaries. To mitigate this issue, many researchers try to introduce external knowledge, such as knowledge graphs and Internet contents, into LLMs for up-to-date information. However, the external information from the Internet may include counterfactual information that will confuse the model and lead to an incorrect response. Thus there is a pressing need for LLMs to possess the ability to distinguish reliable information fr"},"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":"2311.08147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T13:24:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80f99285220e07b649bd68435bd1de18afdc33cf66071fb66b2a70e3a939f0e4","abstract_canon_sha256":"4100b781dbd5ad25c0705aa1408a8af0a1ac6d522c10a9f3d3f66c9e5397dc7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:40.834512Z","signature_b64":"T1RChuWAIDXVw2XEO3eW6ahSSZCOKWxmxweQYZGh3WYjuoAkLVStm0tOONHdp16HkO87J1lqOnvRpacStJFpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e17a3faa2990831d8060d927707ee22ba1f8047ec4821bbcc57e81e5ed9f15","last_reissued_at":"2026-07-05T07:12:40.834023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:40.834023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Hao Zhou, Jie Zhou, Lianzhe Huang, Shicheng Li, Sishuo Chen, Xu Sun, Yi Liu","submitted_at":"2023-11-14T13:24:19Z","abstract_excerpt":"LLMs and AI chatbots have improved people's efficiency in various fields. However, the necessary knowledge for answering the question may be beyond the models' knowledge boundaries. To mitigate this issue, many researchers try to introduce external knowledge, such as knowledge graphs and Internet contents, into LLMs for up-to-date information. However, the external information from the Internet may include counterfactual information that will confuse the model and lead to an incorrect response. Thus there is a pressing need for LLMs to possess the ability to distinguish reliable information fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08147","kind":"arxiv","version":1},"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/2311.08147/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":"2311.08147","created_at":"2026-07-05T07:12:40.834087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08147v1","created_at":"2026-07-05T07:12:40.834087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08147","created_at":"2026-07-05T07:12:40.834087+00:00"},{"alias_kind":"pith_short_12","alias_value":"47QXUP5KFGII","created_at":"2026-07-05T07:12:40.834087+00:00"},{"alias_kind":"pith_short_16","alias_value":"47QXUP5KFGIIGHMA","created_at":"2026-07-05T07:12:40.834087+00:00"},{"alias_kind":"pith_short_8","alias_value":"47QXUP5K","created_at":"2026-07-05T07:12:40.834087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15391","citing_title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02605","citing_title":"Do Audio-Visual Large Language Models Really See and Hear?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02640","citing_title":"Overcoming the \"Impracticality\" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I","json":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I.json","graph_json":"https://pith.science/api/pith-number/47QXUP5KFGIIGHMAMDMSO4D64I/graph.json","events_json":"https://pith.science/api/pith-number/47QXUP5KFGIIGHMAMDMSO4D64I/events.json","paper":"https://pith.science/paper/47QXUP5K"},"agent_actions":{"view_html":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I","download_json":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I.json","view_paper":"https://pith.science/paper/47QXUP5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08147&json=true","fetch_graph":"https://pith.science/api/pith-number/47QXUP5KFGIIGHMAMDMSO4D64I/graph.json","fetch_events":"https://pith.science/api/pith-number/47QXUP5KFGIIGHMAMDMSO4D64I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I/action/storage_attestation","attest_author":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I/action/author_attestation","sign_citation":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I/action/citation_signature","submit_replication":"https://pith.science/pith/47QXUP5KFGIIGHMAMDMSO4D64I/action/replication_record"}},"created_at":"2026-07-05T07:12:40.834087+00:00","updated_at":"2026-07-05T07:12:40.834087+00:00"}