{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QLQYTZHRMAR5AGFCJDEKOSF4KK","short_pith_number":"pith:QLQYTZHR","schema_version":"1.0","canonical_sha256":"82e189e4f16023d018a248c8a748bc5296778863feaf5d20b4d8871eb1cbfc77","source":{"kind":"arxiv","id":"2402.11406","version":3},"attestation_state":"computed","paper":{"title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang-Tien Lu, Jianfeng He, Min Zhang, Taoran Ji","submitted_at":"2024-02-18T00:04:40Z","abstract_excerpt":"The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However, the extent to which LLMs effectively address this issue remains insufficiently examined. This paper delves into the capability of LLMs to detect implicit hate speech (Classification Task) and express confidence in their responses (Calibration Task). Our evaluation meticulously considers various prompt patterns and mainstream uncertainty estimation methods. Our"},"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":"2402.11406","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T00:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"294da4a734dc910c389f21dfd4cec9e2753f06ba61d35ff6c6b8238a31bea233","abstract_canon_sha256":"72998946f45aa069c85b504268bbe023f08efdaf6a5504359e4d2d664867855b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:11.135770Z","signature_b64":"50kk3hoVU29kEDcu3t1lUuMroAnfjQMYWYeO713UIwMD1yZKWsm9RdKxmNGeO2FnCLTZPP/4d9GpUYwvTmTcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e189e4f16023d018a248c8a748bc5296778863feaf5d20b4d8871eb1cbfc77","last_reissued_at":"2026-07-05T08:47:11.135285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:11.135285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang-Tien Lu, Jianfeng He, Min Zhang, Taoran Ji","submitted_at":"2024-02-18T00:04:40Z","abstract_excerpt":"The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However, the extent to which LLMs effectively address this issue remains insufficiently examined. This paper delves into the capability of LLMs to detect implicit hate speech (Classification Task) and express confidence in their responses (Calibration Task). Our evaluation meticulously considers various prompt patterns and mainstream uncertainty estimation methods. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11406","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/2402.11406/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":"2402.11406","created_at":"2026-07-05T08:47:11.135351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11406v3","created_at":"2026-07-05T08:47:11.135351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11406","created_at":"2026-07-05T08:47:11.135351+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLQYTZHRMAR5","created_at":"2026-07-05T08:47:11.135351+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLQYTZHRMAR5AGFC","created_at":"2026-07-05T08:47:11.135351+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLQYTZHR","created_at":"2026-07-05T08:47:11.135351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23930","citing_title":"Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK","json":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK.json","graph_json":"https://pith.science/api/pith-number/QLQYTZHRMAR5AGFCJDEKOSF4KK/graph.json","events_json":"https://pith.science/api/pith-number/QLQYTZHRMAR5AGFCJDEKOSF4KK/events.json","paper":"https://pith.science/paper/QLQYTZHR"},"agent_actions":{"view_html":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK","download_json":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK.json","view_paper":"https://pith.science/paper/QLQYTZHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11406&json=true","fetch_graph":"https://pith.science/api/pith-number/QLQYTZHRMAR5AGFCJDEKOSF4KK/graph.json","fetch_events":"https://pith.science/api/pith-number/QLQYTZHRMAR5AGFCJDEKOSF4KK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK/action/storage_attestation","attest_author":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK/action/author_attestation","sign_citation":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK/action/citation_signature","submit_replication":"https://pith.science/pith/QLQYTZHRMAR5AGFCJDEKOSF4KK/action/replication_record"}},"created_at":"2026-07-05T08:47:11.135351+00:00","updated_at":"2026-07-05T08:47:11.135351+00:00"}