{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VTT3KRZAGU6GB4MHGHUOFHSDVI","short_pith_number":"pith:VTT3KRZA","schema_version":"1.0","canonical_sha256":"ace7b54720353c60f18731e8e29e43aa0c801a690dbe8a274c698de50cb10883","source":{"kind":"arxiv","id":"2411.15287","version":1},"attestation_state":"computed","paper":{"title":"Sycophancy in Large Language Models: Causes and Mitigations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lars Malmqvist","submitted_at":"2024-11-22T16:56:49Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to exhibit sycophantic behavior - excessively agreeing with or flattering users - poses significant risks to their reliability and ethical deployment. This paper provides a technical survey of sycophancy in LLMs, analyzing its causes, impacts, and potential mitigation strategies. We review recent work on measuring and quantifying sycophantic tendencies, examine the relationship between sycophancy and other challenges like hallucination and bia"},"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":"2411.15287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T16:56:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba71620ca4a93d234603932424d02e6b2e67a8d1d2ade0709875c651f9b1aa82","abstract_canon_sha256":"1f0cb350605f6fde6cd52810c5fc863b928ca4dcde8ecfe24c57f1e0b5abd183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:45.928544Z","signature_b64":"irjp4Pffn55uc5OLLcAjLmVL+ETNf3rbOgOnOBkmfaxWpeytYidGD7bImKuD4C0WrJZWTqLd9V5WHKKvoIZQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ace7b54720353c60f18731e8e29e43aa0c801a690dbe8a274c698de50cb10883","last_reissued_at":"2026-07-05T10:06:45.928088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:45.928088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sycophancy in Large Language Models: Causes and Mitigations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lars Malmqvist","submitted_at":"2024-11-22T16:56:49Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to exhibit sycophantic behavior - excessively agreeing with or flattering users - poses significant risks to their reliability and ethical deployment. This paper provides a technical survey of sycophancy in LLMs, analyzing its causes, impacts, and potential mitigation strategies. We review recent work on measuring and quantifying sycophantic tendencies, examine the relationship between sycophancy and other challenges like hallucination and bia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15287","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/2411.15287/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":"2411.15287","created_at":"2026-07-05T10:06:45.928151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15287v1","created_at":"2026-07-05T10:06:45.928151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15287","created_at":"2026-07-05T10:06:45.928151+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTT3KRZAGU6G","created_at":"2026-07-05T10:06:45.928151+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTT3KRZAGU6GB4MH","created_at":"2026-07-05T10:06:45.928151+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTT3KRZA","created_at":"2026-07-05T10:06:45.928151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21569","citing_title":"When Support Escalates Distress: Regulation and Escalation in LLM Responses to Venting and Advice-Seeking","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16727","citing_title":"Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07180","citing_title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06921","citing_title":"Teaching Astronomy with Large Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2506.12605","citing_title":"The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02585","citing_title":"Mitigating LLM biases toward spurious social contexts using direct preference optimization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02668","citing_title":"Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03261","citing_title":"Can AI Help You Get Over Your Breakup? One Session with a Belief-Reframing Chatbot Shows Sustained Distress Reduction","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07369","citing_title":"The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16095","citing_title":"GroupEnvoy: A Conversational Agent Speaking for the Outgroup to Foster Intergroup Relations","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI","json":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI.json","graph_json":"https://pith.science/api/pith-number/VTT3KRZAGU6GB4MHGHUOFHSDVI/graph.json","events_json":"https://pith.science/api/pith-number/VTT3KRZAGU6GB4MHGHUOFHSDVI/events.json","paper":"https://pith.science/paper/VTT3KRZA"},"agent_actions":{"view_html":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI","download_json":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI.json","view_paper":"https://pith.science/paper/VTT3KRZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15287&json=true","fetch_graph":"https://pith.science/api/pith-number/VTT3KRZAGU6GB4MHGHUOFHSDVI/graph.json","fetch_events":"https://pith.science/api/pith-number/VTT3KRZAGU6GB4MHGHUOFHSDVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI/action/storage_attestation","attest_author":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI/action/author_attestation","sign_citation":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI/action/citation_signature","submit_replication":"https://pith.science/pith/VTT3KRZAGU6GB4MHGHUOFHSDVI/action/replication_record"}},"created_at":"2026-07-05T10:06:45.928151+00:00","updated_at":"2026-07-05T10:06:45.928151+00:00"}