{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A6A6V2ILJX2RFKE2NXSQXTN5IM","short_pith_number":"pith:A6A6V2IL","schema_version":"1.0","canonical_sha256":"0781eae90b4df512a89a6de50bcdbd4320d20f7e7fd9915f7d68203f5a613b01","source":{"kind":"arxiv","id":"2509.03518","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs Lie? Investigation beyond Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deepak Pathak, Haoran Huan, Mengning Wu, Mihir Prabhudesai, Shantanu Jaiswal","submitted_at":"2025-09-03T17:59:45Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional falsehoods-have been widely studied, the phenomenon of lying, where an LLM knowingly generates falsehoods to achieve an ulterior objective, remains underexplored. In this work, we systematically investigate the lying behavior of LLMs, differentiating it from hallucinations and testing it in practical scenarios. Through mechanistic interpretability techniques, we "},"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":"2509.03518","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"8cf657ec98035c2c27349af7a764839e0f67ee63998a87cdbfbd2883b897eb31","abstract_canon_sha256":"aabbf08a5df0e6e6dfede8a3db591e76854e06b76cc360d3a821d1aee2f20740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:24.047717Z","signature_b64":"KlgZh+m8+zr25j6jdAkhNGfvViL06GJ9wls9Sg/wwmaJFYKcmAvwUMKDUP0yJ3Nq0/n+kTyV66eeUKE4vRQ7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0781eae90b4df512a89a6de50bcdbd4320d20f7e7fd9915f7d68203f5a613b01","last_reissued_at":"2026-07-05T12:04:24.047220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:24.047220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Lie? Investigation beyond Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deepak Pathak, Haoran Huan, Mengning Wu, Mihir Prabhudesai, Shantanu Jaiswal","submitted_at":"2025-09-03T17:59:45Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional falsehoods-have been widely studied, the phenomenon of lying, where an LLM knowingly generates falsehoods to achieve an ulterior objective, remains underexplored. In this work, we systematically investigate the lying behavior of LLMs, differentiating it from hallucinations and testing it in practical scenarios. Through mechanistic interpretability techniques, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03518","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/2509.03518/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":"2509.03518","created_at":"2026-07-05T12:04:24.047277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03518v1","created_at":"2026-07-05T12:04:24.047277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03518","created_at":"2026-07-05T12:04:24.047277+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6A6V2ILJX2R","created_at":"2026-07-05T12:04:24.047277+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6A6V2ILJX2RFKE2","created_at":"2026-07-05T12:04:24.047277+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6A6V2IL","created_at":"2026-07-05T12:04:24.047277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13310","citing_title":"RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19270","citing_title":"DECOR: Auditing LLM Deception via Information Manipulation Theory","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19117","citing_title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM","json":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM.json","graph_json":"https://pith.science/api/pith-number/A6A6V2ILJX2RFKE2NXSQXTN5IM/graph.json","events_json":"https://pith.science/api/pith-number/A6A6V2ILJX2RFKE2NXSQXTN5IM/events.json","paper":"https://pith.science/paper/A6A6V2IL"},"agent_actions":{"view_html":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM","download_json":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM.json","view_paper":"https://pith.science/paper/A6A6V2IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03518&json=true","fetch_graph":"https://pith.science/api/pith-number/A6A6V2ILJX2RFKE2NXSQXTN5IM/graph.json","fetch_events":"https://pith.science/api/pith-number/A6A6V2ILJX2RFKE2NXSQXTN5IM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM/action/storage_attestation","attest_author":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM/action/author_attestation","sign_citation":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM/action/citation_signature","submit_replication":"https://pith.science/pith/A6A6V2ILJX2RFKE2NXSQXTN5IM/action/replication_record"}},"created_at":"2026-07-05T12:04:24.047277+00:00","updated_at":"2026-07-05T12:04:24.047277+00:00"}