{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IAVOAHVFQB5YLU4A5HRSEJFVCQ","short_pith_number":"pith:IAVOAHVF","schema_version":"1.0","canonical_sha256":"402ae01ea5807b85d380e9e32224b514306a1a9219691ca2830d72d140736ba5","source":{"kind":"arxiv","id":"2403.04307","version":3},"attestation_state":"computed","paper":{"title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yiming Yang, Zhiqing Sun, Zhiying Zhu","submitted_at":"2024-03-07T08:25:46Z","abstract_excerpt":"Hallucinations pose a significant challenge to the reliability of large language models (LLMs) in critical domains. Recent benchmarks designed to assess LLM hallucinations within conventional NLP tasks, such as knowledge-intensive question answering (QA) and summarization, are insufficient for capturing the complexities of user-LLM interactions in dynamic, real-world settings. To address this gap, we introduce HaluEval-Wild, the first benchmark specifically designed to evaluate LLM hallucinations in the wild. We meticulously collect challenging (adversarially filtered by Alpaca) user queries f"},"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":"2403.04307","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T08:25:46Z","cross_cats_sorted":[],"title_canon_sha256":"3b8a03f09bef3c10686337e6c42500ebb8981c4e9561cd7cf1d58ed9be915c40","abstract_canon_sha256":"4d30c365da1982d0adebf503cd7e29fb1def6bf08083105511bd379e5e71f654"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:57.786617Z","signature_b64":"YL1ue+vJi7UkF6ML7Mkei1t7y0EkvYRzGxHAc0vx3eRJqPImmetIJU8LzX3wFEoLrWkO6OmNHlh1R/w7e3KgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402ae01ea5807b85d380e9e32224b514306a1a9219691ca2830d72d140736ba5","last_reissued_at":"2026-07-05T09:06:57.786115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:57.786115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yiming Yang, Zhiqing Sun, Zhiying Zhu","submitted_at":"2024-03-07T08:25:46Z","abstract_excerpt":"Hallucinations pose a significant challenge to the reliability of large language models (LLMs) in critical domains. Recent benchmarks designed to assess LLM hallucinations within conventional NLP tasks, such as knowledge-intensive question answering (QA) and summarization, are insufficient for capturing the complexities of user-LLM interactions in dynamic, real-world settings. To address this gap, we introduce HaluEval-Wild, the first benchmark specifically designed to evaluate LLM hallucinations in the wild. We meticulously collect challenging (adversarially filtered by Alpaca) user queries f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04307","kind":"arxiv","version":3},"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/2403.04307/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":"2403.04307","created_at":"2026-07-05T09:06:57.786179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04307v3","created_at":"2026-07-05T09:06:57.786179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04307","created_at":"2026-07-05T09:06:57.786179+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAVOAHVFQB5Y","created_at":"2026-07-05T09:06:57.786179+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAVOAHVFQB5YLU4A","created_at":"2026-07-05T09:06:57.786179+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAVOAHVF","created_at":"2026-07-05T09:06:57.786179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05680","citing_title":"CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ","json":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ.json","graph_json":"https://pith.science/api/pith-number/IAVOAHVFQB5YLU4A5HRSEJFVCQ/graph.json","events_json":"https://pith.science/api/pith-number/IAVOAHVFQB5YLU4A5HRSEJFVCQ/events.json","paper":"https://pith.science/paper/IAVOAHVF"},"agent_actions":{"view_html":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ","download_json":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ.json","view_paper":"https://pith.science/paper/IAVOAHVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04307&json=true","fetch_graph":"https://pith.science/api/pith-number/IAVOAHVFQB5YLU4A5HRSEJFVCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IAVOAHVFQB5YLU4A5HRSEJFVCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ/action/storage_attestation","attest_author":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ/action/author_attestation","sign_citation":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ/action/citation_signature","submit_replication":"https://pith.science/pith/IAVOAHVFQB5YLU4A5HRSEJFVCQ/action/replication_record"}},"created_at":"2026-07-05T09:06:57.786179+00:00","updated_at":"2026-07-05T09:06:57.786179+00:00"}