{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ERZOW3RII4T3YX3WN6X6E3R6OF","short_pith_number":"pith:ERZOW3RI","schema_version":"1.0","canonical_sha256":"2472eb6e284727bc5f766fafe26e3e7140f9f68399f562c81bde4bdd8ed01b92","source":{"kind":"arxiv","id":"2311.09410","version":4},"attestation_state":"computed","paper":{"title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giulia Pucci, Leonardo Ranaldi","submitted_at":"2023-11-15T22:18:33Z","abstract_excerpt":"Large Language Models have been demonstrating broadly satisfactory generative abilities for users, which seems to be due to the intensive use of human feedback that refines responses. Nevertheless, suggestibility inherited via human feedback improves the inclination to produce answers corresponding to users' viewpoints. This behaviour is known as sycophancy and depicts the tendency of LLMs to generate misleading responses as long as they align with humans. This phenomenon induces bias and reduces the robustness and, consequently, the reliability of these models. In this paper, we study the sug"},"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":"2311.09410","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T22:18:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc350a17c162f29aea8c05733d4d75093039a199970348a191e23446e413b436","abstract_canon_sha256":"247279cbd8293d0a92fa66a519bd76689899443ea679aa289752b987c5b81e10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:41.305309Z","signature_b64":"PkGlboM1KepbJqOISg1aBQR8qGiDq88v8ntO8jleLlXIDOWzzwLn9Gs+xGXY1cj4JhkxTsvmfhf8BLv1CXUIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2472eb6e284727bc5f766fafe26e3e7140f9f68399f562c81bde4bdd8ed01b92","last_reissued_at":"2026-07-05T11:26:41.304836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:41.304836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giulia Pucci, Leonardo Ranaldi","submitted_at":"2023-11-15T22:18:33Z","abstract_excerpt":"Large Language Models have been demonstrating broadly satisfactory generative abilities for users, which seems to be due to the intensive use of human feedback that refines responses. Nevertheless, suggestibility inherited via human feedback improves the inclination to produce answers corresponding to users' viewpoints. This behaviour is known as sycophancy and depicts the tendency of LLMs to generate misleading responses as long as they align with humans. This phenomenon induces bias and reduces the robustness and, consequently, the reliability of these models. In this paper, we study the sug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09410","kind":"arxiv","version":4},"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/2311.09410/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":"2311.09410","created_at":"2026-07-05T11:26:41.304893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09410v4","created_at":"2026-07-05T11:26:41.304893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09410","created_at":"2026-07-05T11:26:41.304893+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERZOW3RII4T3","created_at":"2026-07-05T11:26:41.304893+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERZOW3RII4T3YX3W","created_at":"2026-07-05T11:26:41.304893+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERZOW3RI","created_at":"2026-07-05T11:26:41.304893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18060","citing_title":"PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01071","citing_title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13220","citing_title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10949","citing_title":"Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10158","citing_title":"\"Where is this coming from?\" Uncovering Trustworthiness Ideals in AI-powered Peripartum Information Seeking","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01951","citing_title":"Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06306","citing_title":"Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01071","citing_title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02444","citing_title":"Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10467","citing_title":"User Detection and Response Patterns of Sycophantic Behavior in Conversational AI","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06476","citing_title":"Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05403","citing_title":"When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20652","citing_title":"Large Language Models Outperform Humans in Fraud Detection and Resistance to Motivated Investor Pressure","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05957","citing_title":"Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05279","citing_title":"Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13803","citing_title":"Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF","json":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF.json","graph_json":"https://pith.science/api/pith-number/ERZOW3RII4T3YX3WN6X6E3R6OF/graph.json","events_json":"https://pith.science/api/pith-number/ERZOW3RII4T3YX3WN6X6E3R6OF/events.json","paper":"https://pith.science/paper/ERZOW3RI"},"agent_actions":{"view_html":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF","download_json":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF.json","view_paper":"https://pith.science/paper/ERZOW3RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09410&json=true","fetch_graph":"https://pith.science/api/pith-number/ERZOW3RII4T3YX3WN6X6E3R6OF/graph.json","fetch_events":"https://pith.science/api/pith-number/ERZOW3RII4T3YX3WN6X6E3R6OF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF/action/storage_attestation","attest_author":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF/action/author_attestation","sign_citation":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF/action/citation_signature","submit_replication":"https://pith.science/pith/ERZOW3RII4T3YX3WN6X6E3R6OF/action/replication_record"}},"created_at":"2026-07-05T11:26:41.304893+00:00","updated_at":"2026-07-05T11:26:41.304893+00:00"}