{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:INSEFB6PSLGET262PJUSJM2H55","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ed803faab087df15ad757df6e9c4e649642a883308bb14ed9f4f3e8d79c5000d","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:45:22Z","title_canon_sha256":"160536257ffcc8779c01541c47eb39d8df443f5fea1a2536ffc02ae8454b7d79"},"schema_version":"1.0","source":{"id":"2407.11789","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11789","created_at":"2026-07-05T08:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11789v1","created_at":"2026-07-05T08:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11789","created_at":"2026-07-05T08:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"INSEFB6PSLGE","created_at":"2026-07-05T08:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"INSEFB6PSLGET262","created_at":"2026-07-05T08:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"INSEFB6P","created_at":"2026-07-05T08:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:ac194c5ead77517cfa6655e4019e51c964f2d8ba2cdacde2c450df2189b1fd0c","target":"graph","created_at":"2026-07-05T08:44:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.11789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of LLMs to be deceptive in the context of providing assistance on a reading comprehension task, using LLMs as proxies for human users. We compare outcomes of (1) when the model is prompted to provide truthful assistance, (2) when it is prompted to be subtly misleading, and (3) when it is prompted to argue for an incorrect answer. Our experiments show that GPT-4","authors_text":"Betty Li Hou, James Aung, Jason Phang, Kejian Shi, Rosie Campbell, Steven Adler","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:45:22Z","title":"Large Language Models as Misleading Assistants in Conversation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11789","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0171689b86f894abe0125e9828ecc05169ecd4a89ae93f3a60ba8d61e5d2fc7e","target":"record","created_at":"2026-07-05T08:44:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ed803faab087df15ad757df6e9c4e649642a883308bb14ed9f4f3e8d79c5000d","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:45:22Z","title_canon_sha256":"160536257ffcc8779c01541c47eb39d8df443f5fea1a2536ffc02ae8454b7d79"},"schema_version":"1.0","source":{"id":"2407.11789","kind":"arxiv","version":1}},"canonical_sha256":"43644287cf92cc49ebda7a6924b347ef47a6568bf10b49c0947e42a44741eb53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43644287cf92cc49ebda7a6924b347ef47a6568bf10b49c0947e42a44741eb53","first_computed_at":"2026-07-05T08:44:40.968834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:40.968834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mpEB/0XgIgUZGeQA6cTURNCuKhmYtsBWUZzTzX4FYTbfuJ79Ql3XS4OeQJlz2oYjoAXHMc2s7jx28mDIY13HAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:40.969286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11789","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0171689b86f894abe0125e9828ecc05169ecd4a89ae93f3a60ba8d61e5d2fc7e","sha256:ac194c5ead77517cfa6655e4019e51c964f2d8ba2cdacde2c450df2189b1fd0c"],"state_sha256":"0f0b64b0a6471adc84b2e6f8c9de4a4aa0fb04c273521ab2d3d37150b8b4efa3"}