{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5IXHXOAOPIRNW6Q5YOS7NU22J","short_pith_number":"pith:G5IXHXOA","schema_version":"1.0","canonical_sha256":"375173ddc073d116dbd0ee1d2fb69ad247906ea5ab44c1e2e8484b0f4fd0f345","source":{"kind":"arxiv","id":"2410.00775","version":1},"attestation_state":"computed","paper":{"title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Javier Parapar, Paloma Piot","submitted_at":"2024-10-01T15:16:20Z","abstract_excerpt":"Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistra"},"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":"2410.00775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T15:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"9bf7df4dd761a8d1abd6abf70af5bb2ddefe83a3bd5c1c79cbfef0e59b484b51","abstract_canon_sha256":"6f13b1b5b7d79925082b841cb3f287d18d567478d4c528c28603e16828109e2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:35.963978Z","signature_b64":"h+K2Vitj3cQZd120KbyOc5fjCg6bgAc5GzGTfZ7+CQe0ozt0NjyF/n1V18B77kUMfm/vI3sqgm9zOI5UiVPNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375173ddc073d116dbd0ee1d2fb69ad247906ea5ab44c1e2e8484b0f4fd0f345","last_reissued_at":"2026-07-05T11:17:35.963532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:35.963532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Javier Parapar, Paloma Piot","submitted_at":"2024-10-01T15:16:20Z","abstract_excerpt":"Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00775","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/2410.00775/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":"2410.00775","created_at":"2026-07-05T11:17:35.963589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00775v1","created_at":"2026-07-05T11:17:35.963589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00775","created_at":"2026-07-05T11:17:35.963589+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5IXHXOAOPIR","created_at":"2026-07-05T11:17:35.963589+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5IXHXOAOPIRNW6Q","created_at":"2026-07-05T11:17:35.963589+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5IXHXOA","created_at":"2026-07-05T11:17:35.963589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04043","citing_title":"Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J","json":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J.json","graph_json":"https://pith.science/api/pith-number/G5IXHXOAOPIRNW6Q5YOS7NU22J/graph.json","events_json":"https://pith.science/api/pith-number/G5IXHXOAOPIRNW6Q5YOS7NU22J/events.json","paper":"https://pith.science/paper/G5IXHXOA"},"agent_actions":{"view_html":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J","download_json":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J.json","view_paper":"https://pith.science/paper/G5IXHXOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00775&json=true","fetch_graph":"https://pith.science/api/pith-number/G5IXHXOAOPIRNW6Q5YOS7NU22J/graph.json","fetch_events":"https://pith.science/api/pith-number/G5IXHXOAOPIRNW6Q5YOS7NU22J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J/action/storage_attestation","attest_author":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J/action/author_attestation","sign_citation":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J/action/citation_signature","submit_replication":"https://pith.science/pith/G5IXHXOAOPIRNW6Q5YOS7NU22J/action/replication_record"}},"created_at":"2026-07-05T11:17:35.963589+00:00","updated_at":"2026-07-05T11:17:35.963589+00:00"}