{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AAC35ZKMPVVRVI34KPBIQ4KBCQ","short_pith_number":"pith:AAC35ZKM","schema_version":"1.0","canonical_sha256":"0005bee54c7d6b1aa37c53c2887141143e7f09569a98faabd3af6a1199025647","source":{"kind":"arxiv","id":"2404.09329","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Carrasco-Farre","submitted_at":"2024-04-14T19:01:20Z","abstract_excerpt":"Large Language Models (LLMs) are already as persuasive as humans. However, we know very little about how they do it. This paper investigates the persuasion strategies of LLMs, comparing them with human-generated arguments. Using a dataset of 1,251 participants in an experiment, we analyze the persuasion strategies of LLM-generated and human-generated arguments using measures of cognitive effort (lexical and grammatical complexity) and moral-emotional language (sentiment and moral analysis). The study reveals that LLMs produce arguments that require higher cognitive effort, exhibiting more comp"},"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":"2404.09329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T19:01:20Z","cross_cats_sorted":[],"title_canon_sha256":"62acab8402039fc6f095c51f70eab6ff65cdca8abe12d61ee2038158a32dd6a6","abstract_canon_sha256":"8d26bb23f020c8fa17e0b750a1016d1a65ce80a7a79916dc579450f1678916fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:26.457727Z","signature_b64":"dRdvm643TQK2KjBVhxscyos/D23vIcUHV9UbOzMTOOC0RdRy8mHNePNN14oTisZJAI5yIQtaQOqsbaQ8mZydCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0005bee54c7d6b1aa37c53c2887141143e7f09569a98faabd3af6a1199025647","last_reissued_at":"2026-07-05T08:10:26.457295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:26.457295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos Carrasco-Farre","submitted_at":"2024-04-14T19:01:20Z","abstract_excerpt":"Large Language Models (LLMs) are already as persuasive as humans. However, we know very little about how they do it. This paper investigates the persuasion strategies of LLMs, comparing them with human-generated arguments. Using a dataset of 1,251 participants in an experiment, we analyze the persuasion strategies of LLM-generated and human-generated arguments using measures of cognitive effort (lexical and grammatical complexity) and moral-emotional language (sentiment and moral analysis). The study reveals that LLMs produce arguments that require higher cognitive effort, exhibiting more comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09329","kind":"arxiv","version":2},"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/2404.09329/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":"2404.09329","created_at":"2026-07-05T08:10:26.457368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09329v2","created_at":"2026-07-05T08:10:26.457368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09329","created_at":"2026-07-05T08:10:26.457368+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAC35ZKMPVVR","created_at":"2026-07-05T08:10:26.457368+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAC35ZKMPVVRVI34","created_at":"2026-07-05T08:10:26.457368+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAC35ZKM","created_at":"2026-07-05T08:10:26.457368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05330","citing_title":"A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26233","citing_title":"Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Tools","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22975","citing_title":"When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23867","citing_title":"Human Decision-Making with Persuasive and Narrative LLM Explanations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2411.06837","citing_title":"Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26233","citing_title":"Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Tools","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08321","citing_title":"LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22109","citing_title":"Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04354","citing_title":"Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16935","citing_title":"LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ","json":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ.json","graph_json":"https://pith.science/api/pith-number/AAC35ZKMPVVRVI34KPBIQ4KBCQ/graph.json","events_json":"https://pith.science/api/pith-number/AAC35ZKMPVVRVI34KPBIQ4KBCQ/events.json","paper":"https://pith.science/paper/AAC35ZKM"},"agent_actions":{"view_html":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ","download_json":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ.json","view_paper":"https://pith.science/paper/AAC35ZKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09329&json=true","fetch_graph":"https://pith.science/api/pith-number/AAC35ZKMPVVRVI34KPBIQ4KBCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AAC35ZKMPVVRVI34KPBIQ4KBCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ/action/storage_attestation","attest_author":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ/action/author_attestation","sign_citation":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ/action/citation_signature","submit_replication":"https://pith.science/pith/AAC35ZKMPVVRVI34KPBIQ4KBCQ/action/replication_record"}},"created_at":"2026-07-05T08:10:26.457368+00:00","updated_at":"2026-07-05T08:10:26.457368+00:00"}