{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2DJ6K7LCBUP5CVVKV4TYIKNNM","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":"64fb2f7fa4b7333813a34e497f267bb715908f9b80f392ab8db7884cab3a01e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T16:49:36Z","title_canon_sha256":"b9fc3a92e4895a7e1bf63091966670d07a5971be4b1bfc0bce5c9e2eb58bc839"},"schema_version":"1.0","source":{"id":"2410.14596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14596","created_at":"2026-07-05T10:12:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14596v2","created_at":"2026-07-05T10:12:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14596","created_at":"2026-07-05T10:12:01Z"},{"alias_kind":"pith_short_12","alias_value":"F2DJ6K7LCBUP","created_at":"2026-07-05T10:12:01Z"},{"alias_kind":"pith_short_16","alias_value":"F2DJ6K7LCBUP5CVV","created_at":"2026-07-05T10:12:01Z"},{"alias_kind":"pith_short_8","alias_value":"F2DJ6K7L","created_at":"2026-07-05T10:12:01Z"}],"graph_snapshots":[{"event_id":"sha256:6051441a7ba477fe8cda1200e4a654f1b36c1f0aec350a32ebec0853c09101ed","target":"graph","created_at":"2026-07-05T10:12:01Z","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/2410.14596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are susceptible to persuasion, which can pose risks when models are faced with an adversarial interlocutor. We take a first step towards defending models against persuasion while also arguing that defense against adversarial (i.e. negative) persuasion is only half of the equation: models should also be able to accept beneficial (i.e. positive) persuasion to improve their answers. We show that optimizing models for only one side results in poor performance on the other. In order to balance positive and negative persuasion, we introduce Persuasion-Training (or PBT), ","authors_text":"Elias Stengel-Eskin, Mohit Bansal, Peter Hase","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T16:49:36Z","title":"Teaching Models to Balance Resisting and Accepting Persuasion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14596","kind":"arxiv","version":2},"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:beb016415ea2fb2fe023bcc0f976bedc37e6e3182a55af8e81beb17af777b176","target":"record","created_at":"2026-07-05T10:12:01Z","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":"64fb2f7fa4b7333813a34e497f267bb715908f9b80f392ab8db7884cab3a01e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T16:49:36Z","title_canon_sha256":"b9fc3a92e4895a7e1bf63091966670d07a5971be4b1bfc0bce5c9e2eb58bc839"},"schema_version":"1.0","source":{"id":"2410.14596","kind":"arxiv","version":2}},"canonical_sha256":"2e869f2beb1068fe8ab555793c214d6b2c37012b46964f07b4e3c28a53f26efe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e869f2beb1068fe8ab555793c214d6b2c37012b46964f07b4e3c28a53f26efe","first_computed_at":"2026-07-05T10:12:01.871034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:01.871034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PG3uYyxJVkGGGFsu+mO8OsL8Dt9O4AsPwbxWmMwr5US9EZepDs3FuCBja1GHMQJqvVJVtxFQgtSy9X3P75CBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:01.871549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beb016415ea2fb2fe023bcc0f976bedc37e6e3182a55af8e81beb17af777b176","sha256:6051441a7ba477fe8cda1200e4a654f1b36c1f0aec350a32ebec0853c09101ed"],"state_sha256":"777bbf78b4d6f9cb0a7fc8ff92b8e7c1205d4200a06f25018df27973f0599461"}