{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LS4MEZIWFDIVPBCZGUA73BSSJ7","short_pith_number":"pith:LS4MEZIW","schema_version":"1.0","canonical_sha256":"5cb8c2651628d15784593501fd86524fe5f03b1f6f3dc433e0e4bf5119852739","source":{"kind":"arxiv","id":"2411.11731","version":1},"attestation_state":"computed","paper":{"title":"Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allison Huang, Carlos Mougan, Yulu Niki Pi","submitted_at":"2024-11-18T16:59:59Z","abstract_excerpt":"We explore how large language models (LLMs) can be influenced by prompting them to alter their initial decisions and align them with established ethical frameworks. Our study is based on two experiments designed to assess the susceptibility of LLMs to moral persuasion. In the first experiment, we examine the susceptibility to moral ambiguity by evaluating a Base Agent LLM on morally ambiguous scenarios and observing how a Persuader Agent attempts to modify the Base Agent's initial decisions. The second experiment evaluates the susceptibility of LLMs to align with predefined ethical frameworks "},"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":"2411.11731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T16:59:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac92b1a89cd0271c4f226302a9cd58363316516392aa979be5ae16da5a28ddff","abstract_canon_sha256":"fe850a0c89c0905024ad3955e22bac4feadc90daf10f428bdf0db0c00eb177d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:00.318266Z","signature_b64":"/0Kj9wN17tsiRR7C4ofW+9eUf3DjqOypKOSRmGx8Riexe5SPoOrMxtr79RR4vBlSm6xhxWaJXpujQAjXf9ApAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb8c2651628d15784593501fd86524fe5f03b1f6f3dc433e0e4bf5119852739","last_reissued_at":"2026-07-05T09:37:00.317769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:00.317769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allison Huang, Carlos Mougan, Yulu Niki Pi","submitted_at":"2024-11-18T16:59:59Z","abstract_excerpt":"We explore how large language models (LLMs) can be influenced by prompting them to alter their initial decisions and align them with established ethical frameworks. Our study is based on two experiments designed to assess the susceptibility of LLMs to moral persuasion. In the first experiment, we examine the susceptibility to moral ambiguity by evaluating a Base Agent LLM on morally ambiguous scenarios and observing how a Persuader Agent attempts to modify the Base Agent's initial decisions. The second experiment evaluates the susceptibility of LLMs to align with predefined ethical frameworks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11731","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/2411.11731/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":"2411.11731","created_at":"2026-07-05T09:37:00.317826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11731v1","created_at":"2026-07-05T09:37:00.317826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11731","created_at":"2026-07-05T09:37:00.317826+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS4MEZIWFDIV","created_at":"2026-07-05T09:37:00.317826+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS4MEZIWFDIVPBCZ","created_at":"2026-07-05T09:37:00.317826+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS4MEZIW","created_at":"2026-07-05T09:37:00.317826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02507","citing_title":"What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7","json":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7.json","graph_json":"https://pith.science/api/pith-number/LS4MEZIWFDIVPBCZGUA73BSSJ7/graph.json","events_json":"https://pith.science/api/pith-number/LS4MEZIWFDIVPBCZGUA73BSSJ7/events.json","paper":"https://pith.science/paper/LS4MEZIW"},"agent_actions":{"view_html":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7","download_json":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7.json","view_paper":"https://pith.science/paper/LS4MEZIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11731&json=true","fetch_graph":"https://pith.science/api/pith-number/LS4MEZIWFDIVPBCZGUA73BSSJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/LS4MEZIWFDIVPBCZGUA73BSSJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7/action/storage_attestation","attest_author":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7/action/author_attestation","sign_citation":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7/action/citation_signature","submit_replication":"https://pith.science/pith/LS4MEZIWFDIVPBCZGUA73BSSJ7/action/replication_record"}},"created_at":"2026-07-05T09:37:00.317826+00:00","updated_at":"2026-07-05T09:37:00.317826+00:00"}